status

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Command Execution] (LOW): The skill executes local bash scripts located in the project's hidden .claude directory, including a discovery script and a system-check hook. While standard for this workflow, it relies on the integrity of the local environment.
  • [Prompt Injection] (LOW): The skill processes output from discovery.sh to construct the user-facing status report, representing an indirect injection surface. (1) Ingestion points: Output from .claude/skills/status/scripts/discovery.sh. (2) Boundary markers: None specified; the agent is instructed to directly parse the output. (3) Capability inventory: Bash script execution (restricted to specified paths). (4) Sanitization: No sanitization of the script's YAML output is performed before presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 08:22 PM