gsd-spec-phase
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local environment, which could contain malicious instructions targeting the agent's broad execution capabilities.\n
- Ingestion points: Analyzes project-specific files including PROJECT.md, REQUIREMENTS.md, ROADMAP.md, STATE.md, and general codebase files discovered via Glob and Grep tools.\n
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate ingested data, potentially allowing embedded text to be interpreted as agent commands.\n
- Capability inventory: The skill is configured to use Bash for command execution, Write for file system changes, and AskUserQuestion for user interaction, creating a high-impact surface for exploitation.\n
- Sanitization: There is no evidence of content sanitization or validation performed on the ingested files before they are processed by the agent.
Audit Metadata