tw-research-grounded-theory
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data in the form of research topics and interview/observation transcripts, creating a surface for potential instruction injection.\n
- Ingestion points: User-provided research themes and interview fragments collected in Step 1 of SKILL.md.\n
- Boundary markers: The instructions lack specific delimiters or guardrails to differentiate between analysis data and potential embedded commands.\n
- Capability inventory: The skill's frontmatter configuration allows access to Bash, Read, and Write tools during the analysis process.\n
- Sanitization: There are no instructions or scripts provided to sanitize, escape, or validate the ingested qualitative data before it is processed by the agent.
Audit Metadata