issue-graph

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and Git to perform repository operations, such as querying issues, updating labels, and creating issue relationships. These commands are core to the skill's functionality and are constructed using verified identifiers like issue numbers.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from GitHub issue bodies and comments to determine relationship mapping and task status. It mitigates risk by using deterministic regex and JSON parsing rather than passing untrusted content to an LLM for decision-making. The system uses specific boundary markers such as agent-claim: and spinoff-of: to safely identify metadata within issue text.
  • [SAFE]: The network operations are restricted to communication with the GitHub API via the gh command-line tool, following standard developer automation practices. No credential exfiltration, persistence mechanisms, or obfuscation techniques were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 10:26 PM
Security Audit — agent-trust-hub — issue-graph