ralph-specum-implement
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files like
tasks.mdand.progress.mdto define tasks for sub-agents. This presents a standard surface for indirect prompt injection common in coordination agents. - Ingestion points: Processes
tasks.mdand.progress.md(SKILL.md). - Boundary markers: No explicit boundary markers or delimiters are defined in the delegation logic.
- Capability inventory: Limited to local file system operations on project-specific state files and delegating to the
spec-executorsub-agent (SKILL.md). - Sanitization: The skill does not specify sanitization for the ingested task descriptions.
Audit Metadata