doc-organizer
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local documentation files and directory structures to perform project reorganization and index generation.\n- Ingestion points: The agent utilizes tree and find to analyze the filesystem and reads Markdown file contents to populate README index tables (SKILL.md).\n- Boundary markers: The instructions lack specific delimiters or directives to ignore instructions that might be embedded within the project files being organized.\n- Capability inventory: The skill is capable of executing filesystem modifications such as mkdir and mv across the project directory (SKILL.md).\n- Sanitization: There is no evidence of path validation or content sanitization before external data is used in shell commands or generated indexes.
Audit Metadata