psp-signal-hunt

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by ingesting and processing data from external, untrusted sources.
  • Ingestion points: The workflow in SKILL.md involves fetching content from LinkedIn, blogs, and other public feeds using the WebFetch tool to identify signal candidates.
  • Boundary markers: There are no specific instructions to use delimiters or instructions to ignore potential commands within the fetched external data.
  • Capability inventory: The skill is authorized to use WebFetch, Read, and Grep, and it passes findings to downstream skills for content generation (e.g., claude-cold-email).
  • Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content retrieved from external sources before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:28 PM
Security Audit — agent-trust-hub — psp-signal-hunt