wish-ssh-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and review instructions for a Go-based SSH library. It does not include any executable code, scripts, or network-enabled tools. All code examples provided are for illustrative purposes to assist the agent in identifying secure vs. insecure coding patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external Go source code.
- Ingestion points: Repositories and source files containing 'wish' server implementations.
- Boundary markers: None explicitly defined within the skill instructions.
- Capability inventory: The agent uses its built-in file reading capabilities to perform the review.
- Sanitization: None; the skill requires direct extraction of evidence from the code. The risk is inherent to the code-review task and is managed by the agent's core instruction-following logic.
Audit Metadata