planr-fix
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute arbitrary verification commands, such as tests and build tools, which are defined within the repository (SKILL.md, reference.md). This allows for the execution of code resident in the repository.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted inputs to guide its behavior. Ingestion points: user requests, bug docs, task notes, and failing tests (SKILL.md). Boundary markers: Absent. Capability inventory: File system modification and command execution (SKILL.md, reference.md). Sanitization: Absent.
Audit Metadata