influencer-evaluator
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes untrusted data from external social media and statistics websites to calculate influencer metrics.
- Ingestion points: Content is fetched from the internet via
WebSearchandWebFetchtools (Step 2: Search Public Data). - Boundary markers: The skill instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded in the retrieved web data.
- Capability inventory: The skill is authorized to write files to the filesystem (
~/.claude/cache/influencer/) using theWritetool. - Sanitization: There is no logic provided to sanitize or validate the external data before it is incorporated into the agent's evaluation and report generation process.
Audit Metadata