pentest-output-standards
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines procedures for processing external findings such as vulnerability names, evidence, and tool responses (e.g., '漏洞报告', '验证证据'). This creates an inherent surface for indirect prompt injection if the ingested data contains instructions designed to influence the agent's behavior during report generation.
- Ingestion points: Vulnerability reports, exploitation evidence, and findings from target systems are processed within the templates defined in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore commands embedded within the external findings.
- Capability inventory: The skill utilizes data management tools including
upsert_project_fact,record_vulnerability, andlist/search_project_factsto store and retrieve test data. - Sanitization: There are no explicit instructions to sanitize, escape, or validate the content discovered on target systems before recording it.
Audit Metadata