work-start
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill defines a logical workflow for project management using local files. No malicious commands, exfiltration patterns, or obfuscation were identified.
- [NO_CODE]: The skill consists solely of instructions and does not include executable scripts or external dependencies.
- [PROMPT_INJECTION]: The skill instructs the agent to process data from repository files, creating an indirect prompt injection surface as it ingests content from external sources.
- Ingestion points: The agent reads CONTEXT.md, handoff.md, and progress.txt from the repository root.
- Boundary markers: No specific delimiters or instructions to ignore embedded instructions within these files are provided.
- Capability inventory: The skill is limited to reading files and recommending session transitions; it lacks capabilities for network access, arbitrary code execution, or elevated privileges.
- Sanitization: No content sanitization or validation is applied to the ingested files.
Audit Metadata