docs-writer
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external files within the
packages/anddocs/directories. Maliciously crafted content in these files could theoretically influence the agent's behavior. - Ingestion points: Files located in
packages/anddocs/directories. - Boundary markers: None identified in the skill instructions.
- Capability inventory: File system modifications (
replace,write_file) and execution of project scripts (npm run format). - Sanitization: No explicit sanitization or validation of the ingested content is performed.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to propose the execution of
npm run format. This executes a script defined in the localpackage.jsonfile. While routine for formatting documentation, users should ensure that project-level scripts are trusted before execution.
Audit Metadata