apply-program-theme-extractor

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill workflow involves searching for and fetching data from external academic, consortium, and funding websites to extract program themes, which introduces a potential attack surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through web search results and the multi-pass fetching process (Pass A and Pass B) described in the Workflow section of SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the external content.
  • Capability inventory: The skill utilizes web search but does not demonstrate capabilities for command execution, file system modification, or network exfiltration.
  • Sanitization: No methods for sanitizing, escaping, or validating the fetched external content are mentioned in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 05:32 PM
Security Audit — agent-trust-hub — apply-program-theme-extractor