adopt-context-docs
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads from and writes to project instruction files (e.g., AGENTS.md, CLAUDE.md) that govern agent behavior.
- Ingestion points: Processes existing project instructions, entry points, and workspace files to identify the target project and current configuration (SKILL.md).
- Boundary markers: Does not specify the use of delimiters or instructions to ignore embedded commands within the ingested content.
- Capability inventory: Updates persistent agent instruction files and creates or maintains project documentation markers (SKILL.md).
- Sanitization: No explicit sanitization or content validation is mentioned when merging new guidance into existing instruction files.
- [NO_CODE]: The skill consists exclusively of markdown instructions and YAML metadata. No scripts, executables, or binary files are provided within the skill package.
Audit Metadata