aeo-strategist

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes a /research mode that utilizes the web_search tool to collect live competitive intelligence from external sources such as Perplexity, Wikidata, and industry publications. Because the skill does not provide the agent with explicit instructions to delimit or ignore potential malicious instructions embedded within these external search results, it presents a surface for indirect prompt injection.
  • Ingestion points: External data ingested via the /research mode in SKILL.md.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to isolate untrusted web data from the agent's core instructions.
  • Capability inventory: The skill leverages the agent's web_search capability to process external content.
  • Sanitization: There are no documented procedures for the agent to sanitize or filter the content retrieved from web searches before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:14 AM
Security Audit — agent-trust-hub — aeo-strategist