plan-interview
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of all skill files, including instructions and reference guides, confirms the absence of malicious commands, hardcoded credentials, or unauthorized network operations. The skill primarily focuses on documentation and structured dialogue.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external project plans.
- Ingestion points: The agent reads project plan markdown files as input for the interview process.
- Boundary markers: No specific delimiters are defined in the instructions to isolate the ingested plan content from the system prompt.
- Capability inventory: The skill's functionality is limited to reading and writing markdown files; it does not request capabilities for shell command execution, remote code downloads, or network access.
- Sanitization: No sanitization or validation logic is applied to the ingested data prior to its use in the interview context.
Audit Metadata