crabpot-perf-metrics
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses established tools like the GitHub CLI to fetch data from a trusted source. No malicious persistence, privilege escalation, or obfuscation was found.
- [PROMPT_INJECTION]: The skill ingests performance reports from external sources, which creates a potential surface for indirect prompt injection attacks. 1. Ingestion points: reports/crabpot-dashboard-data.json and related JSON profiles in SKILL.md. 2. Boundary markers: The skill does not provide explicit markers or instructions to treat the ingested data as untrusted content. 3. Capability inventory: The skill uses
gh apifor data retrieval and summarizes output, representing a read-heavy capability tier with network access. 4. Sanitization: No sanitization or validation of the external JSON structure is performed.
Audit Metadata