release
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's workflow requires the agent to execute various scripts found within the repository environment.
- Evidence: Step 3 of the workflow in
SKILL.mdinstructs the agent to "Run relevant tests, typecheck, lint, build, packaging, migration, and smoke checks." - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes external data sources that could contain malicious instructions.
- Ingestion points: Commit history, merged pull request descriptions, and changelog entries as defined in
SKILL.md(Workflow Step 2). - Boundary markers: Absent. The instructions do not specify any delimiters or safety warnings for the agent when processing this data.
- Capability inventory: The agent has the ability to modify local files (manifests, changelogs) and execute arbitrary local commands (tests, builds, migrations).
- Sanitization: Absent. No filtering or validation steps are defined for the content of processed metadata.
Audit Metadata