adr
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill is purely instructional and provides a framework for documentation within a project. It does not include any scripts, external dependencies, or network-active components.
- [INDIRECT_PROMPT_INJECTION]: The skill monitors and processes files within specific documentation directories.
- Ingestion points: Files matching
docs/decisions/**/*.md,**/decisions/**/*.md, and**/adr/**/*.md. - Boundary markers: None defined in the instructions.
- Capability inventory: The skill is limited to reading and generating documentation content; it contains no subprocess calls, network exfiltration commands, or privilege escalation mechanisms.
- Sanitization: No content sanitization or validation is specified. Despite the ingestion surface, the lack of exploitable capabilities results in a safe assessment for this category.
Audit Metadata