decision-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The README.md file contains a link to download the skill package from the author's GitHub repository (github.com/synapseradio). This is an expected vendor distribution channel and is considered a safe resource.
- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection by ingesting untrusted data from the user and interpolating it into a visualization template. This is a common functional pattern for reporting skills.
- Ingestion points: User-supplied input processed via Phase 0 ($ARGUMENTS).
- Boundary markers: Not explicitly defined for the HTML template interpolation process.
- Capability inventory: File manipulation (copying and writing to assets/template.html) and opening the resulting file.
- Sanitization: The skill instructions do not explicitly require sanitization of user-provided content before it is placed into the tpl markers in the HTML template.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No evidence of sensitive file access, credential harvesting, or unauthorized network communication was found. The skill operates on the logic and data provided by the user within the context of the decision analysis.
Audit Metadata