sdd-tasks
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from project artifacts (proposals, specs, designs) to generate task lists. While this represents a theoretical attack surface where instructions inside those artifacts could attempt to influence the generated tasks, the skill's narrow scope (producing a markdown checklist) and lack of executable capabilities minimize the risk. Evidence:
- Ingestion points: Reads artifacts via
mem_get_observationor filesystem (SKILL.md). - Boundary markers: None explicit for input data; output is constrained to a specific markdown checklist format.
- Capability inventory: Memory persistence (
mem_save) and filesystem writes (SKILL.md). - Sanitization: None specified for input artifact content.- [COMMAND_EXECUTION]: The skill uses platform-specific tools (
mem_search,mem_get_observation,mem_save) to manage state and project data. These operations are consistent with the skill's stated purpose of orchestrating task breakdowns within a structured development workflow.
Audit Metadata