Is obra/superpowers safe?
What obra/superpowers does
Superpowers is a software development methodology for coding agents, built from composable skills, such as test-driven development, plus initial instructions that make the agent use them. The README says it is built by Prime Radiant; it lives in obra/superpowers and is distributed through plugin marketplaces for Claude Code, Codex, Grok and other agents. It injects a bootstrap through a session-start hook, and its skills direct the agent to read and write files and run commands. Before installing, read the hook and the skills it adds, since they change how your agent behaves in every session.
- Possible command injection (exec with dynamic command)
- Node.js shell/command execution
- Python filesystem read
What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.
obra/superpowers is a GitHub repository analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 1 risky construct is reported for review. It can: filesystem read, filesystem write, network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 20/100 (low).
superpowers 7.0.2
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 obra/superpowers'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 (6)
The code builds an OS command out of values that can change at runtime, then runs it through a shell.
try { cp.exec(process.env.BRAINSTORM_OPEN_CMD + ' ' + JSON.stringify(url), () => {}); } catch (e) { /* best effort */ }Why it matters: If any of those values come from untrusted input, an attacker can run their own commands on the machine.
Fix: Use execFile/spawn with an argument array instead of exec; never build a shell command string from external input.
The component can run operating-system commands or spawn processes.
const cp = require('child_process');try { cp.exec(process.env.BRAINSTORM_OPEN_CMD + ' ' + JSON.stringify(url), () => {}); } catch (e) { /* best effort */ }import { execFileSync } from 'child_process';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; prefer execFile with an argument array.
The component reads files from disk.
const fullContent = fs.readFileSync(skillPath, 'utf8');
const { frontmatter, content } = extractAndStripFrontmatter(fs.readFileSync(skillPath, 'utf8'));const p = Number(fs.readFileSync(PORT_FILE, 'utf-8').trim());
const t = fs.readFileSync(TOKEN_FILE, 'utf-8').trim();
const frameTemplate = fs.readFileSync(path.join(__dirname, 'frame-template.html'), 'utf-8');
const helperScript = fs.readFileSync(path.join(__dirname, 'helper.js'), 'utf-8');
const data = JSON.parse(fs.readFileSync(manifest, 'utf-8'));
? (raw => isFullDocument(raw) ? raw : wrapInFrame(raw))(fs.readFileSync(screenFile, 'utf-8'))
res.end(fs.readFileSync(filePath));
const markdown = fs.readFileSync(skillFile, 'utf-8');
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.
fs.appendFileSync(eventsFile, JSON.stringify(event) + '\n');
if (fs.existsSync(eventsFile)) fs.unlinkSync(eventsFile);
if (fs.existsSync(infoFile)) fs.unlinkSync(infoFile);
fs.writeFileSync(
try { fs.writeFileSync(PORT_FILE, String(PORT)); } catch (e) { /* best effort */ }fs.writeFileSync(TOKEN_FILE, TOKEN, { mode: 0o600 });fs.writeFileSync(path.join(STATE_DIR, 'server-info'), info + '\n', { mode: 0o600 });fs.writeFileSync(outputPath, svg);
fs.writeFileSync(dotPath, combined);
fs.writeFileSync(outputPath, svg);
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 reads files from disk.
with open(
os.path.join(skills_dir, "using-superpowers", "SKILL.md"),
encoding="utf-8",
) as f:with open(tools_path, encoding="utf-8") as f:
with open(skill_md, 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 makes outbound network requests.
const http = require('http');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.
How attackers abuse these capabilities
Interactive labs on the attack class behind the rules above. They show the technique, not anything found in obra/superpowers.
Maintain obra/superpowers?
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 →