lore-maintain
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external data from documentation and source code, creating a surface for embedded instructions to influence the agent.
- Ingestion points: The skill ingests content from glossary.md, terms.md, CONTEXT.md, and any source code file linked via code: tags in lore entries.
- Boundary markers: There are no specific instructions or delimiters provided to the agent to distinguish between the maintenance instructions and potentially malicious content within the files being processed.
- Capability inventory: The skill possesses the capability to read from the file system, modify existing documentation files, and archive or delete files.
- Sanitization: No sanitization or validation protocols are defined for the content extracted from the processed files.
Audit Metadata