annual-report-charity-bureau

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection via document ingestion. Although the skill has no dangerous capabilities, malicious instructions within user-provided documents could influence the generated report's content.
  • Ingestion points: Document gathering in 'Pre-Draft Intake' (SKILL.md).
  • Boundary markers: Absent; no specific instructions provided to the agent to ignore potential commands within the data.
  • Capability inventory: No subprocess calls, exec/eval, file-write, or network operations are defined in the skill (SKILL.md).
  • Sanitization: No evidence of data sanitization or input validation for external documents.
  • [NO_CODE]: The skill consists solely of a Markdown file (SKILL.md) containing instructions and templates, with no referenced scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 07:56 PM