intent-signal-aggregator
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources such as job postings, news articles, and company announcements. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the content being monitored to influence the agent's output or actions.
- Ingestion points: External web sources mentioned in instructions (SKILL.md), including job listings, TechCrunch articles, and company-published content.
- Boundary markers: Absent. The instructions do not provide delimiters or warnings to the agent to ignore instructions embedded within the intent signals.
- Capability inventory: None. The skill file contains no code, though its logic relies on the agent having web-browsing or search capabilities.
- Sanitization: Absent. There are no instructions for filtering or sanitizing the retrieved data.
- [NO_CODE]: The skill consists entirely of instructional markdown and metadata. It does not include any Python scripts, Node.js code, or shell commands, which significantly limits the risk of direct malicious execution.
Audit Metadata