The Agent Skills Directory

[SAFE]: The skill primarily consists of instructional content and strategic advice. Comprehensive scanning for obfuscation, malicious network operations, privilege escalation, and persistence mechanisms yielded no findings.
[PROMPT_INJECTION]: The skill defines a workflow for indirect data ingestion via research tools such as exa-company-research, exa-people-research, and exa-personal-site to identify prospect signals. While this introduces a surface for indirect prompt injection from external websites, the risk is inherent to the research use-case and the skill lacks dangerous executable capabilities.
Ingestion points: Tool invocations for external research specified in the 'Signal-Based Outreach' section of SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are defined for the fetched external content.
Capability inventory: The skill triggers other specialized skills including cold-email, sales-qualification, and structured-log.
Sanitization: No explicit validation or filtering logic is defined for data returned by the research tools.

founder-sales