site-reliability-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool for routine project maintenance, such as running npm scripts (
npm run validate:all) and clearing build caches (rm -rf .docusaurus build). These commands are standard for the described SRE role. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external Markdown and MDX files.
- Ingestion points: Files are read by
scripts/validate-liquid.js,scripts/validate-brackets.js, andscripts/validate-skill-props.js. - Boundary markers: None identified; the scripts process file content in its entirety.
- Capability inventory: The skill has access to filesystem tools (Read, Write, Edit, Glob) and command execution (Bash).
- Sanitization: The scripts use static regular expressions to identify and report specific formatting errors. This logic does not execute the processed data or interpolate it into the agent's core instruction set, significantly limiting the risk of injection.
- [EXTERNAL_DOWNLOADS]: The CI/CD reference materials recommend official GitHub Actions (e.g.,
actions/checkout@v3,actions/setup-node@v3). These originate from a trusted organization and are documented neutrally as standard configuration for automated workflows.
Audit Metadata