pr-hero
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npx -y pr-heroto execute the utility, which downloads the package from the npm registry if not present. As this refers to the author's own software, it is a standard operational pattern.\n- [COMMAND_EXECUTION]: The skill involves running local shell commands such aspr-hero config,pr-hero doctor, andpr-hero reviewto manage and use the tool. These commands are intended for the skill's primary purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes repository-level files and pull request content, representing an attack surface for indirect injection. \n - Ingestion points: Repository files
gotchas.md,.prheroignore, and pull request diffs. \n - Boundary markers: No explicit delimiters or boundary markers for untrusted content are defined in the instructions. \n
- Capability inventory: Execution of local shell commands via the
pr-heroCLI. \n - Sanitization: No sanitization or escaping mechanisms for external content are specified.
Audit Metadata