x-hook-extractor

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted tweet and thread text pasted by users to perform classification and template generation.
  • Ingestion points: In SKILL.md, the agent is instructed to ask the user to paste the tweet or thread text (Step 2).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate untrusted data from the agent's logic.
  • Capability inventory: Based on SKILL.md and its referenced files, the skill is limited to text analysis and response generation; it does not utilize network tools, file system writes, or subprocess execution.
  • Sanitization: No input validation or instruction filtering is performed on the ingested text to prevent embedded prompts from influencing the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 11:36 AM
Security Audit — agent-trust-hub — x-hook-extractor