affinity-diagram
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns such as credential theft, unauthorized command execution, or data exfiltration were detected. The skill's logic is restricted to organizing and analyzing text data.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to ingest untrusted data from external files.
- Ingestion points: The instructions in
SKILL.mddirect the agent to read user-provided files, including interview notes, observation data, and survey responses. - Boundary markers: Absent. There are no instructions to use delimiters or ignore potentially malicious commands that might be embedded within the qualitative data.
- Capability inventory: The skill has no high-risk capabilities; it does not invoke subprocesses, perform file-system writes, or initiate network connections, which limits the potential impact of any injection.
- Sanitization: No evidence of input validation or sanitization of the research data was found.
Audit Metadata