kb-index
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local markdown files to generate index entries, which could allow malicious instructions in those files to influence agent behavior. 1. Ingestion points: The skill reads frontmatter and overviews from files in the Projects, Areas, Resources, and Archive directories. 2. Boundary markers: The instructions do not specify the use of delimiters or warnings to the agent to ignore instructions embedded in the ingested content. 3. Capability inventory: The skill utilizes file read, file write, and directory listing (Glob) capabilities. 4. Sanitization: No explicit sanitization or validation of the extracted metadata is performed before it is written to the index files.
Audit Metadata