fetch-watchlist-sources

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from various external web sources, including blogs and social media feeds. This creates a potential surface for indirect prompt injection attacks, where malicious instructions hidden in the fetched content could influence the agent's subsequent behavior.\n
  • Ingestion points: The skill performs web fetches from listing and archive URLs defined in ops/trend-scout/watchlist.md.\n
  • Boundary markers: The workflow does not explicitly define delimiters to separate untrusted web content from the agent's instructions.\n
  • Capability inventory: The skill records the results of the fetches into local cache files (.cache/YYYY-WW-raw.jsonl).\n
  • Sanitization: No data validation or content sanitization steps are specified for the external information retrieved.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 02:36 PM
Security Audit — agent-trust-hub — fetch-watchlist-sources