clade-known-pitfalls
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read, analyze, and modify a user's codebase to implement Anthropic API best practices. This ingestion of local file content creates a surface where instructions embedded in the source code could potentially influence the agent's behavior during the audit process.
- Ingestion points: Local source code files accessed via standard Read, Write, and Edit tools (SKILL.md).
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided to separate user code content from agent instructions.
- Capability inventory: The skill possesses the ability to Read, Write, and Edit files, allowing for broad modification of the local development environment (SKILL.md).
- Sanitization: No specific sanitization, validation, or filtering of the analyzed code content is defined.
Audit Metadata