learn
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves analyzing arbitrary project files, which serves as an ingestion point for untrusted data. Maliciously crafted content within the codebase could attempt to influence the sub-agent's analysis or the rules it generates.
- Ingestion points: The learn-analyst sub-agent reads and analyzes files in the current working directory.
- Boundary markers: None. There are no explicit instructions or delimiters used to prevent the agent from following instructions embedded in the analyzed code.
- Capability inventory: The skill has access to Write, Edit, and Bash tools, which are used to persist the learned rules.
- Sanitization: The process lacks content sanitization or escaping mechanisms for the data extracted from the project files.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to perform environment checks and project sizing. While the implemented commands (ls, cat, find, wc) are standard discovery tools, they execute directly in the project's shell environment.
Audit Metadata