mitre

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it interpolates untrusted finding descriptions into its analysis flow.
  • Ingestion points: Findings are ingested from .appsec/findings.json and user-provided file paths as described in SKILL.md.
  • Boundary markers: Absent; the skill does not wrap findings in delimiters or provide instructions to ignore embedded commands.
  • Capability inventory: Safe; no subprocess calls, network operations, or file-writing capabilities were identified in the skill instructions.
  • Sanitization: Absent; the skill performs structural validation but does not filter or sanitize the textual content of findings.
  • [NO_CODE]: This skill is entirely instructional (markdown) and does not ship with any executable code, scripts, or library dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 06:45 PM