skills/open-hax/eta-mu-pi/fork-tax/Gen Agent Trust Hub

fork-tax

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git CLI tools to manage the repository state. It executes commands such as git status to identify changes, git add for staging (with a preference for path-scoped staging), git commit to persist changes, and git tag for versioning.
  • [DATA_EXFILTRATION]: The skill performs network operations by executing git push to send the repository's local commits and tags to a remote server. This behavior is the stated primary purpose of the skill to facilitate handoffs and state persistence.
  • [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface because it reads and processes the working directory to generate handoff artifacts like .ημ/Π_STATE.sexp and .ημ/Π_LAST.md.
  • Ingestion points: Reads the working tree and git status output.
  • Boundary markers: None identified in the artifact generation instructions.
  • Capability inventory: Perform git commits, tags, and network pushes.
  • Sanitization: The skill includes instructions to stop and redact if secrets are suspected, but does not specify automated sanitization for metadata generated from file contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 06:48 PM
Security Audit — agent-trust-hub — fork-tax