100 / tool / 33

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data sources, creating a surface for Indirect Prompt Injection (Category 8).
  • Ingestion points: The prompt instructions in SKILL.md designate 'user questions' and 'full conversation' as the primary and secondary evidence for the agent to follow.
  • Boundary markers: The skill lacks explicit delimiters (like XML tags or triple quotes) or specific 'ignore instructions' warnings to separate the untrusted data from the agent's logic.
  • Capability inventory: The skill is primarily instructional and does not define automated tools, shell execution, or network access within its files.
  • Sanitization: No sanitization, escaping, or validation steps are included for the data processed from the conversation sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 04:48 AM
Security Audit — agent-trust-hub — 100 / tool / 33