cmd-rss-feed-review

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze RSS feed XML files which contain content from external websites. This creates a surface for indirect prompt injection where malicious instructions embedded in a feed could attempt to influence the agent during the review process.
  • Ingestion points: The agent reads XML files in the 'feeds/' directory and Python scripts in 'feed_generators/'.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within the feed data are provided.
  • Capability inventory: The agent's actions are limited to analyzing text and generating a review report.
  • Sanitization: The instructions do not specify sanitization or validation of the feed content before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 07:56 PM
Security Audit — agent-trust-hub — cmd-rss-feed-review