herdr-issue-coordinator

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes data from external sources that can be controlled by third parties.
  • Ingestion points: The skill reads issue descriptions, pull request comments, and project board metadata in the Preconditions and State Rules sections of SKILL.md.
  • Boundary markers: No specific delimiters or safety warnings are used to wrap external content when it is passed into worker agent prompts.
  • Capability inventory: The skill can execute shell commands via git and herdr, and it can modify GitHub repository state (merging/closing) via the gh CLI.
  • Sanitization: There is no evidence of content sanitization or validation for the data ingested from GitHub.
  • [COMMAND_EXECUTION]: The skill executes local system commands using git worktree and the herdr CLI to manage developer workspaces and orchestrate sub-agent sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 07:40 AM
Security Audit — agent-trust-hub — herdr-issue-coordinator