research-tech-stack
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow includes executing a local script
node scripts/validate-wiki.mjslocated within the repository to validate documentation changes. This is a controlled execution of a local project utility. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it fetches and processes data from external web sources.
- Ingestion points: Web search results and content from external documentation sites (Workflow steps 4 and 5 in
SKILL.md). - Boundary markers: Absent; there are no specific instructions to use delimiters or ignore instructions embedded in the retrieved web content.
- Capability inventory: Reading/writing wiki files and executing the
node scripts/validate-wiki.mjsscript (Workflow steps 8, 10, and 11 inSKILL.md). - Sanitization: Present; the agent is instructed to verify source applicability and synthesize only relevant information, which provides a layer of logical filtering.
Audit Metadata