consult-adrs
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and follow instructions from Architectural Decision Records (ADRs) located in the project's docs/adr/ and adr/ directories. • Ingestion points: The skill reads content from all .md files within the specified ADR directories in SKILL.md. • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used; the agent is instructed to treat these records as authoritative constraints on its work. • Capability inventory: The skill uses awk for metadata parsing and instructs the agent to read file contents to influence design, planning, and implementation. • Sanitization: There is no validation or sanitization of the content within these ADR files before the agent processes them as authoritative project rules.
Audit Metadata