offensive-phishing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to identify and inspect external entrypoints, trust boundaries, and configuration files, creating a surface for indirect prompt injection.
- Ingestion points: The workflow in
SKILL.mdinvolves 'Surface & Architecture Inventory' and 'static code/binary inspection' of external assets. - Boundary markers: The instructions lack specific delimiters or guidance for the agent to treat data from analyzed artifacts as untrusted or to ignore embedded instructions.
- Capability inventory: The skill refers to integration with orchestration and reporting tools (
rea-universal-orchestrator,offensive-reporting) which could be misused if the agent is influenced by poisoned data from the audit target. - Sanitization: No sanitization or filtering protocols are defined for the data ingested during the auditing process.
Audit Metadata