gsd-plan-milestone-gaps
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads content from local audit files, creating a surface for indirect prompt injection if those files contain untrusted data.
- Ingestion points: The skill reads data from
.planning/v*-MILESTONE-AUDIT.mdfiles using Glob and Read tools. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the ingested file content.
- Capability inventory: The skill utilizes
Bash,Write, andAskUserQuestiontools, which provides a functional path for potentially injected instructions to modify the system or filesystem. - Sanitization: There is no explicit mention of sanitizing or validating the content of the audit files before the agent processes them.
Audit Metadata