write-docs
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read, review, and draft documentation artifacts (READMEs, PR descriptions, guides). This creates an ingestion surface for untrusted data that could contain indirect prompt injections designed to influence the agent's behavior during analysis or generation.
- Ingestion points: The skill reads various markdown files from the repository (e.g., README.md, PR descriptions) and passes them to the
prose_lint.pyscript. - Boundary markers: The skill mentions
<!-- prose-lint-ignore -->for ignoring specific lines in the linter, but lacks robust delimiters to prevent the agent from obeying instructions embedded within the target artifacts. - Capability inventory: The skill executes a local Python linter and reads project files.
- Sanitization: No sanitization or escaping of external content is performed before the agent processes the prose.
- [COMMAND_EXECUTION]: The skill involves the execution of a local utility script,
scripts/prose_lint.py, to perform automated clarity checks. The included test suite,scripts/test_prose_lint.py, usessubprocess.runto invoke this utility during verification. These are standard operations for the skill's purpose.
Audit Metadata