The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js script to perform a state check before proceeding.
Evidence: node scripts/run-state-check.js positioning in SKILL.md.
[PROMPT_INJECTION]: The skill processes external 'Evidence' data, such as customer quotes, which serves as a vector for indirect prompt injection if the ingested data contains malicious instructions.
Ingestion points: The skill body in SKILL.md references processing 'Evidence' and 'ICP' (Ideal Customer Profile) data.
Boundary markers: None present; the instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within the evidence.
Capability inventory: The skill utilizes shell command execution via the node environment.
Sanitization: There is no mention of escaping, filtering, or validating the input evidence before it is processed by the agent.

positioning