task-estimation
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as task descriptions and acceptance criteria. This creates a surface for indirect prompt injection if the input contains malicious instructions designed to override agent behavior.
- Ingestion points: Task descriptions and acceptance criteria fields in the provided estimation templates (SKILL.md).
- Boundary markers: No specific boundary markers or 'ignore' instructions are present to delimit user-provided task descriptions from the agent's instructions.
- Capability inventory: The skill is configured with 'Read', 'Write', 'Grep', and 'Glob' tools which provide a wide surface for data manipulation if the agent follows injected instructions.
- Sanitization: There are no instructions for sanitizing or escaping the content of task descriptions before they are processed or included in output documents.
Audit Metadata