live-verify
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several git commands (e.g., git fetch, git rev-parse, git rev-list, git log, and git diff) to determine the state of the local development environment relative to the upstream repository.
- [COMMAND_EXECUTION]: Employs the GitHub CLI (gh issue list) to query the ffroliva/gflow-cli repository for existing issues matching specific error signatures encountered during verification.
- [EXTERNAL_DOWNLOADS]: Communicates with GitHub servers via git fetch and the GitHub API (through the gh tool) to synchronize repository data and fetch issue metadata. These interactions involve a well-known service and are consistent with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data. * Ingestion points: Data enters the agent context from the output of gh issue list (external GitHub issue titles) and from the local KNOWN_ISSUES.md file. * Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are specified for the processed issue data. * Capability inventory: The skill utilizes git and gh for command execution and writes evidence logs to the local file system at tmp/live-verify/. * Sanitization: No specific sanitization or escaping mechanisms are mentioned for handling the error text search or issue results.
Audit Metadata