analyze
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external text files (recordings), which presents a surface for indirect prompt injection where malicious instructions embedded in the recordings could influence agent behavior.
- Ingestion points: The skill reads user-provided
.txtfiles as defined in thefileargument inSKILL.md. - Boundary markers: The workflow does not specify the use of delimiters or 'ignore' instructions to isolate the data being analyzed from the agent's core logic.
- Capability inventory: The skill leverages the
Bashtool to runripgrepand usesReadto access file contents. - Sanitization: No evidence of sanitization, escaping, or validation of the external file content is present in the skill definition.
Audit Metadata