changelog-monitor

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external, untrusted sources.
  • Ingestion points: External URLs provided via the url or project parameters are processed by the browser_json tool in SKILL.md (Step 2).
  • Boundary markers: There are no explicit boundary markers or instructions to the model to ignore embedded commands within the fetched changelog content.
  • Capability inventory: The skill itself does not possess high-risk capabilities like file system modification or shell execution; it primarily performs data extraction and summarization.
  • Sanitization: There is no evidence of sanitization or filtering applied to the fetched text before it is summarized by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 09:52 PM
Security Audit — agent-trust-hub — changelog-monitor