reputation-audit
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted social media posts which serve as an ingestion point for potential instructions meant to override the AI's rubric.
- Ingestion points: The skill fetches an account's own posts from x.com for processing via the browser script (
scripts/reputationAudit.js) or CLI tool. - Boundary markers: The documentation does not specify the use of delimiters (e.g., XML tags or unique markers) or specific 'ignore embedded instructions' prompts to isolate post content from the scoring logic.
- Capability inventory: The skill features a 'one-click cleanup' mechanism that can perform account actions (deleting posts) based on the AI-generated risk score.
- Sanitization: There is no mention of sanitizing or filtering post content before it is interpolated into the prompt for the LLM.
Audit Metadata