repo-standardizer
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
ghCLI,git,jq, andpython3to audit and modify GitHub repository settings, labels, and configuration files. This includes creating commits, pushing to remote repositories, and making authenticated API calls to manage repository rulesets. - [INDIRECT_PROMPT_INJECTION]: The skill audits existing repository content (e.g., file existence, contents of
package.json,pyproject.toml) to determine the repository's state and which templates to apply. - Ingestion points: Repository metadata and file contents fetched from the target GitHub repository via
gh apiandgit. - Boundary markers: None explicitly used during data interpolation from the target repository.
- Capability inventory:
gitoperations (clone, commit, push),ghAPI writes (label creation, ruleset updates), and file system writes. - Sanitization: Employs
jqfor JSON parsing and a Python one-liner for URL-encoding label names, reducing the risk of injection into API paths.
Audit Metadata