skills/sebas-aikon-intelligence/antigravity-awesome-skills/subagent-driven-development/Gen Agent Trust Hub
subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from implementation plan files, creating an attack surface for instructions embedded in external data.
- Ingestion points: The controller reads implementation plan files (e.g.,
docs/plans/feature-plan.md) to extract task text and context for subagents (SKILL.md). - Boundary markers: The prompt templates (
implementer-prompt.md,spec-reviewer-prompt.md) paste task descriptions and requirements directly into subagent prompts without explicit delimiters or instructions to ignore embedded commands. - Capability inventory: The skill dispatches subagents with capabilities to modify the file system, execute tests, and commit code changes using the
general-purposeandsuperpowerstoolsets (SKILL.md,implementer-prompt.md). - Sanitization: There is no evidence of sanitization, filtering, or validation of the plan content before it is interpolated into subagent instructions.
Audit Metadata