abstraction-police
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing project source code to detect architectural violations, which serves as an ingestion point for untrusted data from the codebase.
- Ingestion points: The agent is instructed to map intended layers and modules by analyzing imports and grepping source files (SKILL.md).
- Boundary markers: The instructions lack specific guidance on using delimiters or markers to separate the source code content from the agent's instructions, nor do they include warnings to ignore embedded instructions in comments or strings.
- Capability inventory: The skill possesses capabilities to modify source code, add linting/test rules to the project, and generate pull request content (SKILL.md).
- Sanitization: There are no requirements for sanitizing or validating the ingested code content before it is used to influence the agent's refactoring logic or reporting output.
Audit Metadata