port-features
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and process untrusted external content, specifically source code and git history from 'upstream' repositories, which exposes the agent to indirect prompt injection risks.
- Ingestion points: Untrusted data enters the agent context through the instructions to 'read the feature's real files' and 'read path-scoped git log' in SKILL.md.
- Boundary markers: The instructions lack specific boundary markers or safety warnings to ignore instructions found within the processed code or history files.
- Capability inventory: The agent is expected to use file system operations (read/write/copy) and git tools (checkout/log) as described in SKILL.md, providing a pathway for injected instructions to influence the workspace.
- Sanitization: No sanitization, escaping, or validation of the external repository content is performed before the agent processes it.
Audit Metadata