skill-validator
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically 'bunx markdownlint-cli' and a local repository script './scripts/validate-skill-sync.sh', to perform validation tasks.
- [EXTERNAL_DOWNLOADS]: The skill uses the 'bunx' runner to fetch and execute the 'markdownlint-cli' package from the public NPM registry.
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted 'SKILL.md' files and passes their contents to shell-based tools, creating a vector for instructions embedded in those files to influence agent behavior.
- Ingestion points: Processes 'SKILL.md' and related markdown files within the 'skills/' directory.
- Boundary markers: Absent. The instructions do not provide explicit delimiters or warnings to ignore instructions contained within the files being validated.
- Capability inventory: The skill executes shell commands (bunx, local scripts) and performs file system read operations.
- Sanitization: No content sanitization or validation of input files is performed before they are passed to the linting tools or the local validation script.
Audit Metadata