The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in conjunction with highly sensitive local project context.
Ingestion points: Processes arbitrarily provided external inputs including URLs, pastes, and third-party repositories as described in the Process section of SKILL.md.
Boundary markers: The instructions lack clear delimiters or specific guidance to treat external content strictly as data, which may allow instructions hidden in the input to be interpreted as commands by the agent.
Capability inventory: The skill directs the agent to read sensitive local files such as user-profile, tech stack notes, and the memory index, and to perform search operations (grep) on the local workspace.
Sanitization: No sanitization, validation, or filtering logic is specified for handling the external content before it is processed in the same context as sensitive local information.

personalise