cold-outreach-sequence

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection vulnerability surface.
  • Ingestion points: The skill instructs the agent to perform web_search calls to gather research on prospects as defined in SKILL.md.
  • Boundary markers: No delimiters or specific instructions to ignore embedded commands are used for the data retrieved from search results.
  • Capability inventory: The skill is limited to generating text-based outreach sequences such as LinkedIn messages and emails; it does not possess capabilities like file system access or system command execution.
  • Sanitization: No sanitization or content validation is performed on the information returned by the search tool before it is processed by the agent.
  • [NO_CODE]: The skill consists exclusively of markdown instructions and templates with no executable code or external scripts included.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 11:29 PM