net-autopilot
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
python3 scripts/autopilot/autopilot.pyto automate Git operations and API interactions with GitHub and Azure DevOps. - [PROMPT_INJECTION]: The skill processes untrusted content from story files located at
artifacts/stories/ACF-###*.mdand interpolates them into its workflow, creating an indirect prompt injection surface. - Ingestion points:
artifacts/stories/*.md(mentioned in SKILL.md) - Boundary markers: None identified in the provided instructions.
- Capability inventory: Shell execution via
python3(scripts likely perform file-write, git operations, and network API calls). - Sanitization: No sanitization or validation logic is described for the content of the external story files.
- [NO_CODE]: The skill references executable scripts in the
scripts/autopilot/directory that are not present in the provided file list, meaning the agent would be unable to execute the core functionality locally.
Audit Metadata