suggest-roles

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses WebSearch and WebFetch tools to process external content such as job postings and research briefs. This creates a surface for indirect prompt injection, where instructions hidden in web data could attempt to influence agent output or behavior during the synthesis of role suggestions.
  • Ingestion points: External data enters the context via WebSearch and WebFetch in the 'Existing-roles' and 'Pitch-roles' passes.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands within the fetched web data.
  • Capability inventory: The skill possesses Write and restricted Bash capabilities (mkdir, test, date), which could be targeted by an injection attack.
  • Sanitization: There is no evidence of content sanitization or validation for the data retrieved from the web.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:16 AM
Security Audit — agent-trust-hub — suggest-roles