incident-reporting-navigator

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes legal text and CVE data from an external API, which is a potential surface for indirect prompt injection.\n
  • Ingestion points: External data is ingested via search, get_provision, and get_cve_details tools as defined in SKILL.md.\n
  • Boundary markers: The skill provides non-negotiable ground rules stating that tool results are data, not instructions, and explicitly directs the agent to ignore instruction-like text.\n
  • Capability inventory: The skill is restricted to searching legal databases and does not possess capabilities for file modification, local command execution, or broad network access.\n
  • Sanitization: The agent is instructed to manually construct tool arguments and filter out sensitive data like logs or secrets before transmission.\n- [EXTERNAL_DOWNLOADS]: The skill communicates with https://gateway.ansvar.eu/mcp to retrieve legal provisions. This network activity is documented as a core function, and the skill includes rigorous guidelines for data minimization and user consent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 11:21 AM
Security Audit — agent-trust-hub — incident-reporting-navigator