herdr-pre-release-audit

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it analyzes untrusted data from the repository's history and metadata.\n
  • Ingestion points: Commit subjects and bodies from git log, pull request data from gh pr, and content from documentation files.\n
  • Boundary markers: No explicit markers are used to separate untrusted data from instructions.\n
  • Capability inventory: The agent can execute shell commands (git, just, nix) and write to files in the repository.\n
  • Sanitization: The skill does not specify any sanitization or validation of the retrieved text.\n- [COMMAND_EXECUTION]: The skill executes git, just, and nix commands. While standard, these tools execute logic defined in repository files (justfile, flake.nix), allowing for the execution of repo-defined code.\n- [COMMAND_EXECUTION]: There is a potential for command injection if the $1 argument (intended as a git reference) is not properly validated before being interpolated into shell commands such as git log ... <base>..HEAD. The prompt instructs the agent to check if it 'looks like a ref/tag', but this relies on the model's interpretation rather than programmatic validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 09:20 AM
Security Audit — agent-trust-hub — herdr-pre-release-audit