sp-writing-plans
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external specification or requirement documents to generate implementation plans. This creates a vulnerability surface where malicious instructions hidden in the input specification could potentially influence the plan's tasks or the subsequent behavior of the agent.
- Ingestion points: The
SKILL.mdfile defines a workflow that consumes a "spec or requirements" document as the primary input for plan generation. - Boundary markers: The provided prompt templates and instructions do not define clear delimiters or "ignore embedded instructions" warnings when processing the input specification.
- Capability inventory: The skill generates plans that include shell commands (e.g.,
git commit,pytest) intended for execution by other skills (sp-subagent-driven-developmentorsp-executing-plans). - Sanitization: There is no mention of sanitization, validation, or escaping of the content ingested from the external specification files.
Audit Metadata