skills/tobi/qmd/release/Gen Agent Trust Hub

release

Warn

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: MEDIUMPERSISTENCECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PERSISTENCE]: The scripts/install-hooks.sh script modifies the local .git/hooks directory to install a pre-push hook. This ensures that the script scripts/pre-push is executed automatically whenever a git push command is issued. While this is a documented feature of the skill, the installation is performed silently by scripts/release-context.sh (redirecting output to /dev/null), which can obscure the modification of the repository's configuration.\n- [COMMAND_EXECUTION]: The skill instructions and scripts execute various shell commands and local scripts, including git, jq, awk, gh, and several .sh files located within the scripts/ directory. It is important to note that the content of scripts/release.sh, scripts/extract-changelog.sh, and scripts/pre-push was not provided in the analyzed file set.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes untrusted data from the repository, including commit messages and CHANGELOG.md content, to generate release highlights and changelogs.\n
  • Ingestion points: scripts/release-context.sh ingests output from git log and the contents of CHANGELOG.md.\n
  • Boundary markers: The provided scripts do not use specific delimiters or instructions to prevent the agent from following potential commands embedded within commit messages or changelog entries.\n
  • Capability inventory: The skill has the ability to write to files (CHANGELOG.md, package.json), execute local shell scripts, and perform network operations via git push and the GitHub CLI (gh).\n
  • Sanitization: There is no evidence of sanitization or filtering of the ingested git metadata before it is presented to the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 18, 2026, 08:59 AM