one-initiative-summary

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data fetched from an external source without explicit safety boundaries.\n
  • Ingestion points: Initiative data fetched using the list-initiatives tool in SKILL.md.\n
  • Boundary markers: Absent; the prompt does not provide delimiters or instructions to ignore embedded commands in the initiatives array.\n
  • Capability inventory: The skill calls list-initiatives and initiative-summary tools as described in SKILL.md.\n
  • Sanitization: No sanitization or validation of the fetched initiative data is performed before it is passed to the summary tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:47 AM
Security Audit — agent-trust-hub — one-initiative-summary