diataxis
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
scripts/check-links.py) and repository-specific documentation tools (formatter, linter, build). This is consistent with its purpose as a technical documentation assistant. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided documentation files which are treated as untrusted data.
- Ingestion points: Documentation files within the target directory specified in the
path/to/docsargument. - Boundary markers: None identified; the agent reads documentation content directly to perform audits and restructures.
- Capability inventory: Capability to execute shell commands (Python script and repository tools) as defined in the
Validatesection ofSKILL.md. - Sanitization: No explicit sanitization or instruction to ignore embedded directives within the processed documentation is provided.
Audit Metadata