The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes untrusted data from external blueprints, creating a risk that malicious instructions embedded in incident logs or pull request descriptions could influence the agent's behavior.
Ingestion points: Data is ingested through list_entities and get_entity calls targeting blueprints like pull_request, incident, and config_change in SKILL.md.
Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious content embedded within the retrieved data.
Capability inventory: The agent has the capability to write to external systems using the update_incident_investigation tool as described in Step 6 of SKILL.md.
Sanitization: There are no documented steps for validating, escaping, or sanitizing the content of entities retrieved from Port before they are used in the investigation report.

investigate-incident