adr
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from the docs/adr/ directory and the AGENTS.md file to determine constraints before modifying code. This creates a surface for indirect prompt injection where instructions in existing ADRs could influence behavior.
- Ingestion points: The agent reads all markdown files within the docs/adr/ directory and the index section of the project's AGENTS.md file.
- Boundary markers: No specific delimiters or safety warnings are defined to separate the data content of an ADR from the agent's operational instructions.
- Capability inventory: The agent possesses capabilities to read files, write new markdown files, and update existing index files.
- Sanitization: There is no explicit sanitization or validation of the ADR content mentioned to verify the safety of the content before the agent adopts its constraints.
Audit Metadata