absolute-spec
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill automatically scans the codebase, including documentation (README, CLAUDE.md, CONTRIBUTING.md), commit history, and package manifests. This creates a surface where malicious instructions embedded in the codebase could influence the generated design specification or the agent's behavior during the design process.
- Ingestion points: Step 1 (SCAN) reads various files from the project root, the
docs/directory, and recent commit messages to ground the spec in the current state of the code. - Boundary markers: The instructions do not specify the use of delimiters or explicit warnings to ignore embedded instructions within the files being scanned.
- Capability inventory: The skill can read files throughout the codebase, write design documents to
docs/plans/, and chain into the/absolute-workskill for implementation. - Sanitization: There are no instructions to sanitize, escape, or filter the content retrieved from the codebase before it is synthesized into the design specification.
Audit Metadata