ClawAudit verdict

sf-scraper

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill uses browser automation to scrape employee data from a logged-in SAP SuccessFactors browser session. While it does not appear to have malicious intent, it does use potentially risky capabilities.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

98
security
70
transparency
70
maintenance

Findings (2)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("Password") and emits it outward ("attach"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · - **Login page detected** (look for: "Log in", "Username", "Password", "Company ID" fields) → Tell user to log in first and re-attach the relay. - **Session exp

Pattern match low

Popular HTTP library — network access

SKILL.md · prose · downgraded · Got

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API