Is Agentic SEO Skill safe?
- Python shell/command execution
- Python filesystem read
- Python filesystem write/delete
What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.
Agentic SEO Skill is an agent skill analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: delegated authentication, filesystem read, filesystem write, network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
agentic-seo-skill 3.0.1
Get notified when this component changes
Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Agentic SEO Skill's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (5)
The component can run operating-system commands or spawn processes.
result = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
result = subprocess.run(
["gh", "--version"],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
text=True,
)result = subprocess.run(
["gh", "auth", "status", "-h", "github.com"],
capture_output=True,
text=True,
check=False,
timeout=12,
)output = subprocess.check_output(
["git", "remote", "get-url", "origin"],
cwd=cwd,
stderr=subprocess.DEVNULL,
text=True,
).strip()result = subprocess.run(
cmd,
input=input_data,
capture_output=True,
text=True,
timeout=timeout,
check=False,
)result = subprocess.run(cmd, capture_output=True, text=True, check=False)
completed = subprocess.run(args, check=False, capture_output=True, text=True, timeout=timeout)
output = subprocess.check_output(
["git", "for-each-ref", "--sort=-creatordate", "--format=%(refname:short)%09%(creatordate:iso8601)", f"--count={limit}", "refs/tags"],
cwd=cwd,
stderr=subprocess.DEVNULL, …Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.
Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; avoid shell=True.
The component reads files from disk.
with open(source, "r", encoding="utf-8") as fh:
return path.read_text(encoding="utf-8"), "", {"url": source, "status": None, "headers": {}, "error": None}with open(source, "r", encoding="utf-8") as fh:
with open(path, newline="", encoding="utf-8-sig") as fh:
with open(source, "r", encoding="utf-8") as fh:
return path.read_text(encoding="utf-8"), "", {"url": source, "status": None, "headers": {}, "error": None}with open(source, "r", encoding="utf-8") as fh:
text = path.read_text(encoding="utf-8")
with open(path, "r", encoding="utf-8") as fh:
with open(args.findings_json, "r", encoding="utf-8") as f:
with open(args.context_json, "r", encoding="utf-8") as f:
return path.read_text(encoding="utf-8"), "", {"url": source, "status": None, "headers": {}, "error": None}with open(source, "r", encoding="utf-8") as fh:
with open(path, "r", encoding="utf-8") as f:
with open(html_path, "r", encoding="utf-8", errors="ignore") as f:
with open(args.query_file, "r", encoding="utf-8") as f:
with open(path, "r", encoding="utf-8") as f:
markdown = read_text(args.readme_path)
with open(args.query_file, "r", encoding="utf-8") as f:
with open(args.query_file, "r", encoding="utf-8") as f:
return path.read_text(encoding="utf-8"), "", {"url": source, "status": None, "headers": {}, "error": None}return path.read_text(encoding="utf-8"), "", {"url": source, "status": None, "headers": {}, "error": None}payload = json.loads(Path(path).read_text(encoding="utf-8"))
return open(path, "r", encoding="utf-8", errors="replace")
with open(real_path, "r", encoding="utf-8") as f:
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
The component writes or deletes files on disk.
with open(path, "w", encoding="utf-8") as f:
with open(args.output, "w", encoding="utf-8") as f:
os.unlink(html_path)
with open(path, "w", encoding="utf-8") as f:
with open(args.output, "w", encoding="utf-8") as f:
with open(args.output, "w", encoding="utf-8") as f:
with open(args.output, "w", encoding="utf-8") as f:
with open(args.output, "w", encoding="utf-8") as f:
with open(args.output, "w", encoding="utf-8") as f:
with open(args.markdown, "w", encoding="utf-8") as f:
with open(args.action_plan, "w", encoding="utf-8") as f:
with open(args.output, "w", encoding="utf-8") as f:
with open(path, "a", encoding="utf-8") as f:
with open(path, "w", encoding="utf-8") as f:
Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.
Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.
The component makes outbound network requests.
import requests
import requests
import requests
import requests
requester = session or requests.Session()
raise requests.exceptions.TooManyRedirects(f"Too many redirects (max {max_redirects})")raise requests.exceptions.TooManyRedirects(f"Too many redirects (max {max_redirects})")import requests
import requests
import requests
import requests
import requests
import requests
import requests
Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.
Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.
An OAuth 2.0 / OpenID Connect delegated-authentication flow was detected (authorization-code / refresh-token / token-exchange grant, an OIDC authorize/discovery endpoint or id_token, or a delegation library). Tools authenticate with the end user's delegated, scoped credentials rather than a long-lived embedded service credential.
pip install google-api-python-client google-auth-oauthlib
Fix: Delegated auth is a lower-blast-radius execution context than an embedded static credential. Confirm the requested scopes are minimal and that tokens are never logged or forwarded off-host.
How attackers abuse these capabilities
Interactive labs on the attack class behind the rules above. They show the technique, not anything found in Agentic SEO Skill.
Maintain Agentic SEO Skill?
The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →