account-fit-rank

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is entirely instructional (Markdown) and does not contain any executable scripts, binaries, or command-line operations.
  • [SAFE]: No hardcoded credentials, API keys, or sensitive environment variable references were detected.
  • [PROMPT_INJECTION]: The skill workflow processes external data from sources like LinkedIn posts and website changes, which presents a surface for indirect prompt injection.
  • Ingestion points: User-supplied account lists (CSV/names) and external data enrichment (LinkedIn, funding news, website changes) in Step 4.
  • Boundary markers: Absent; the instructions do not specify delimiters to isolate external content from the agent's logic.
  • Capability inventory: The skill is purely instructional and does not include subprocess execution, dynamic code execution, or file-writing tools.
  • Sanitization: Absent; the skill relies on the agent's ability to summarize and extract relevant signals rather than applying programmatic filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:10 PM
Security Audit — agent-trust-hub — account-fit-rank