ln-130-tasks-docs-creator
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches shared reference files and documentation templates from the author's official GitHub repository (github.com/levnikolaevich) using the WebFetch tool when local shared resources are not found. This is a standard mechanism for retrieving updated templates from the vendor.
- [PROMPT_INJECTION]: The skill performs validation of local project documentation (docs/tasks/README.md and docs/tasks/kanban_board.md), creating an entry point for indirect prompt injection. Malicious instructions embedded in these files could theoretically influence the agent during the validation loop.
- Ingestion points: docs/tasks/README.md, docs/tasks/kanban_board.md.
- Boundary markers: Absent.
- Capability inventory: File modification (Edit tool), file discovery (Glob tool), and network access (WebFetch tool).
- Sanitization: No explicit sanitization or escaping of content read from project files is performed before processing.
Audit Metadata