list-feeds-skill

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes content fetched from an external social media platform, which creates a surface for indirect prompt injection if the ingested data contains malicious instructions.
  • Ingestion points: External feed data is ingested from the MCP server in 'scripts/list-feeds.mjs'.
  • Boundary markers: The skill does not use any boundary markers or instructions to isolate untrusted content from the agent's primary instructions.
  • Capability inventory: The agent is granted Bash and Read tools, which could be exploited if malicious instructions embedded in the feed content are followed.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the feed content before it is parsed and logged to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 08:25 AM