wiki-query
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external content from a user's markdown wiki to synthesize answers.
- Ingestion points: The agent reads
index.md,Overview.md, and any user-created markdown files identified within the designated wiki root (referenced inSKILL.md). - Boundary markers: The skill instructions do not specify the use of delimiters or provide instructions to the model to ignore embedded commands within the ingested files.
- Capability inventory: The skill is restricted to filesystem read and write operations on markdown files; it does not have the capability to execute shell commands or initiate network requests.
- Sanitization: There is no evidence of sanitization or validation logic for the content read from the markdown files.
Audit Metadata