plan-interview
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted plan files.
- Ingestion points: The
/plan-interview:interview [plan-file]command inSKILL.mdingests content from an external file provided by the user. - Boundary markers: The skill does not define any boundary markers (such as XML tags or delimiters) or instructions to the agent to treat the input file content as data only, leaving it open to instruction override attacks.
- Capability inventory: The skill has the capability to read input files and write output to
docs/feature-plan-spec.md, which could be exploited if the input file contains instructions to exfiltrate data or write malicious content. - Sanitization: There is no evidence of content sanitization or validation for the ingested plan data before it is processed by the AI agent.
Audit Metadata