tw-research-qualitative-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests and processes qualitative data provided by the user, creating a surface for potential injection attacks.
- Ingestion points: The skill explicitly requests users to provide interview transcripts, focus group records, or observation notes for analysis (identified in
SKILL.md). - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the qualitative data and system instructions, nor are there warnings to ignore instructions embedded within the transcripts.
- Capability inventory: The skill is configured with
Bash, Read, Writetools (as seen in the YAML frontmatter), which could be targeted if an attacker embeds malicious commands within the analysis data. - Sanitization: No sanitization or filtering logic is present to validate the content of the ingested text samples before processing.
Audit Metadata