The Agent Skills Directory

[PROMPT_INJECTION]: The orchestration protocol involves interpolating external data such as error messages and test file contents into agent briefs, creating a potential surface for indirect prompt injection. * Ingestion points: External test files and error logs used to populate agent briefs as described in the 'Approach' and 'Agent Brief Structure' sections (SKILL.md). * Boundary markers: Absent; the provided templates do not use delimiters or instructions to ignore embedded commands in the ingested data. * Capability inventory: Dispatched agents are explicitly tasked with fixing code, which requires file-write and execution capabilities (SKILL.md). * Sanitization: No sanitization or validation of the ingested data is specified before interpolation into the briefs.

parallel-execution