The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize data from user-provided files within a knowledge base.
Ingestion points: The skill reads from wiki/index.md, wiki/sources/, and files within the raw/ directory.
Boundary markers: There are no explicit instructions or delimiters used to ensure the agent ignores malicious instructions that might be embedded within the wiki files.
Capability inventory: The skill utilizes Bash, Read, Write, Edit, Glob, and Grep tools, which could be leveraged if an injection is successful.
Sanitization: No sanitization or validation of the content read from the wiki is performed before it is processed by the agent.
[COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands to perform searches.
Evidence: The skill checks for the existence of a utility using command -v qmd and executes searches using qmd search "query terms" --path wiki/. This is standard functionality for the skill's intended purpose.

second-brain-query