discovery-interviews-surveys

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill content is restricted to Markdown documentation and a JSON rubric for research quality evaluation. It does not request any sensitive permissions or tool access.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes processes for analyzing qualitative research data (such as interview transcripts and open-ended survey results), which involves the ingestion of untrusted content.
  • Ingestion points: The workflow in SKILL.md and the thematic coding instructions in resources/methodology.md require the agent to process external text provided by the user.
  • Boundary markers: The templates and methodologies do not explicitly define delimiters to separate raw data from the agent's analytical instructions.
  • Capability inventory: The skill lacks any dangerous capabilities, such as shell execution or network exfiltration, meaning an injection through transcript data would be unable to perform high-impact actions.
  • Sanitization: No specific sanitization or filtering logic is suggested for incoming research data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:06 AM
Security Audit — agent-trust-hub — discovery-interviews-surveys