finishing-development
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill identifies and executes shell commands retrieved from project configuration files (e.g., Makefile, package.json, README). This allows the agent to run repository-defined scripts as part of the verification process.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it executes commands derived from untrusted project data.
- Ingestion points: Makefile, Taskfile, package.json, README, and local scripts.
- Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands in the source files.
- Capability inventory: Full shell command execution via the agent's environment.
- Sanitization: Absent; the skill does not validate or sanitize the commands found in the repository before execution.
Audit Metadata