compound-refresh
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests and processes untrusted data from documentation files.
- Ingestion points: Files located under the docs/solutions/ directory and MEMORY.md.
- Boundary markers: The instructions do not specify the use of delimiters or sanitization when processing the content of these files.
- Capability inventory: The skill has capabilities to write to the filesystem (updating, replacing, or archiving files in docs/solutions/) and perform Git operations (committing, branching, and opening PRs).
- Sanitization: There is no mention of sanitizing or escaping the content read from files before it is processed by the agent or subagents.
Audit Metadata