spec-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local project files during its 'Bestandsaufnahme' (Inventory) phase, which could be exploited to influence the agent's behavior if those files contain malicious instructions.
- Ingestion points: Reads
CLAUDE.md,AGENTS.md,README.md,package.json, and various source code files in Phase 1 to establish project context. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands when reading these external files, increasing the risk that embedded instructions in the data could be followed.
- Capability inventory: The skill has the capability to read any file in the project and write new Markdown files (
SPEC.mdorCC_PROMPT.md) to the filesystem. - Sanitization: There is no mention of sanitizing, escaping, or validating the content read from the project files before it is interpolated into the final specification or the autonomy prompt generated for other agents.
Audit Metadata