holistic-linting-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the orchestrator to read and act upon reports generated by sub-agents (e.g.,
.claude/reports/linting-resolution-*.md). - Ingestion points: The agent reads files from the
.claude/reports/directory in Step 2 and Step 4 to determine subsequent actions. - Boundary markers: No boundary markers or specific "ignore instructions" directives are specified for the report reading process.
- Capability inventory: The orchestrator maintains the ability to read files and delegate tasks to other sub-agents based on the content of these reports.
- Sanitization: The skill does not implement sanitization or validation of the report content before it influences the agent's workflow.
Audit Metadata