limitation-weaver
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external file content and writes updates to the file system, which constitutes a potential attack surface for data-driven influence.
- Ingestion points: The agent reads data from output/WRITER_SELFLOOP_TODO.md, sections/S*.md, and outline/writer_context_packs.jsonl to inform its rewriting process.
- Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' warnings for the text being processed.
- Capability inventory: The skill has the capability to write modifications to the local filesystem (sections/S*.md).
- Sanitization: No explicit sanitization, validation, or filtering of the input content is performed before the agent processes and interpolates the text.
Audit Metadata