pasta-scope

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is an instructional markdown file that defines a methodology for technical scope mapping. It does not contain executable code, scripts, or commands that could be used for malicious purposes.
  • [PROMPT_INJECTION]: No evidence of prompt injection patterns was found. The skill does not attempt to override system instructions or bypass safety filters.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies ingestion points for potentially untrusted data in Workflow Steps 1 and 2, which scan route files, API specifications (OpenAPI/Swagger/GraphQL), Dockerfiles, and Infrastructure-as-Code manifests. Ingestion points: SKILL.md (Step 1 & 2 files). Boundary markers: None explicitly defined. Capability inventory: The skill provides instructions for textual analysis and report generation only; it does not define capabilities for subprocess execution or network operations. Sanitization: Not mentioned. Assessment: While these ingestion points represent an attack surface, the process is fundamental to the skill's purpose of security analysis, and no exploitable logic is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 06:45 PM