The Agent Skills Directory

[DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses the user's local configuration at ~/.obsidian-wiki/config and the document vault at $OBSIDIAN_VAULT_PATH. This behavior is entirely consistent with the skill's purpose as a knowledge retrieval tool and does not involve sending data to external or untrusted destinations.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files in the user's wiki vault which could potentially contain malicious content meant to influence the agent.
Ingestion points: Files located within the directory defined by the OBSIDIAN_VAULT_PATH environment variable.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to isolate retrieved content from the agent's core logic.
Capability inventory: The skill employs Grep for searching, Read for accessing content, and a semantic search tool via mcp__qmd__query. It also maintains a local activity log in log.md.
Sanitization: There is no evidence of sanitization or content validation before the retrieved text is used to synthesize a response for the user.

wiki-query