itsol-task-intake
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input in the form of task requests to classify work and route tasks to other domain skills. This creates an indirect prompt injection surface where a malicious request could attempt to subvert the agent's classification logic.\n
- Ingestion points: The skill begins by inspecting the "request" and "repository context" in SKILL.md.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the request are defined.\n
- Capability inventory: The skill is designed to load and route to several other skills (itsol-workflow-mode, itsol-repo-memory, itsol-functional-planning, itsol-requirements-review, itsol-execution-policy). It does not contain direct file-write or network-access code.\n
- Sanitization: No sanitization or validation logic for the input request is present.
Audit Metadata