to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes conversation context and codebase files to generate a specification. This creates a surface where malicious instructions embedded in the ingested data could influence the agent's output or actions when publishing to the issue tracker.
- Ingestion points: Conversation context and codebase content (referenced in SKILL.md process steps).
- Boundary markers: None specified to delimit ingested content from generated instructions.
- Capability inventory: Capability to publish to an issue tracker, which likely involves write access to a repository via CLI tools like
gh. - Sanitization: No sanitization or validation of the synthesized content is described before publication.
- [COMMAND_EXECUTION]: The skill instructs the agent to publish synthesized content to a project issue tracker. While specific commands aren't provided in the skill, the execution of this task typically requires the use of command-line interfaces (e.g., GitHub CLI) to create issues.
Audit Metadata