sdd-tasks

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes documents such as proposals, specifications, and designs to create a task list, which presents a surface for indirect prompt injection. Malicious instructions embedded within these source documents could potentially influence the agent's task generation logic.
  • Ingestion points: The skill retrieves the full content of proposal, spec, and design artifacts using the mem_get_observation tool (SKILL.md).
  • Boundary markers: There are no explicit markers or instructions directing the agent to ignore embedded commands or treat the retrieved content as untrusted data.
  • Capability inventory: The skill is capable of writing markdown files to the local filesystem (in the openspec/ directory) and persisting task data to the memory system via mem_save (SKILL.md).
  • Sanitization: No sanitization, validation, or structural filtering of the source artifact content is performed prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:23 PM