piv-run-full-loop
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input via the
$ARGUMENTSvariable and interpolates it directly into instructions for downstream autonomous skills. - Ingestion points: The feature description provided via
$ARGUMENTSinSKILL.mdis passed to thepiv-plan-implementationskill. - Boundary markers: Absent. The skill does not use delimiters or specific instructions to isolate the user input from the agent's core instructions.
- Capability inventory: The skill chains to other components that perform file system modifications and Git operations.
- Sanitization: Absent. The user-provided feature description is used without validation or escaping.
- [COMMAND_EXECUTION]: The skill is designed to orchestrate high-autonomy tasks including codebase priming, plan generation, code implementation, and version control commits. This behavior is the primary purpose of the skill but grants the agent significant autonomy over the local environment based on user input.
Audit Metadata