atlas-adr
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from the local repository (specifically git history and existing ADR files) without using boundary markers or sanitization. Malicious commit messages or file content could potentially influence the AI's output. * Ingestion points: SKILL.md (instructions to read git log and existing ADR files). * Boundary markers: Absent. * Capability inventory: SKILL.md (utilizes Bash tool for git operations, Write and Edit for file modification, and has access to WebFetch tools). * Sanitization: Absent. The instructions do not include steps to filter or validate content retrieved from the repository before processing.
Audit Metadata