performance-report

Pass

Audited by Gen Agent Trust Hub on May 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted performance data which creates a surface for indirect prompt injection where malicious data could attempt to influence the agent's analysis or output.
  • Ingestion points: User-provided performance data (CSV or raw text) in SKILL.md.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions for the data.
  • Capability inventory: Low; the skill is limited to analysis and report formatting using the analytics-analyst agent with no shell or network access.
  • Sanitization: Absent; no specific validation or filtering of input data is mentioned in the process.
Audit Metadata
Risk Level
SAFE
Analyzed
May 23, 2026, 08:33 PM
Security Audit — agent-trust-hub — performance-report