svg-hero-generator
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository files (such as README.md and build manifests) to inform its design process, creating a surface where malicious instructions in project documentation could influence agent behavior.
- Ingestion points: The skill reads README.md, package.json, and other repository metadata files during its initial inspection phase (SKILL.md Pass 1).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' markers to separate untrusted content from core instructions.
- Capability inventory: The agent has access to file system tools (view, bash_tool), executes a local Python helper script (scripts/repo_signals.py), and generates new SVG files.
- Sanitization: No explicit sanitization or filtering of external repository text is mandated before processing by the model.
Audit Metadata