6 tagged agent safety, measured the same way as everything else here.
Agent
Read-only auditor that scans files, directories, URLs, and MCP tool descriptions for prompt-injection attempts. Reports hidden text, override phrases, exfil constructs, fake structural markers, repo-poisoning artifacts, and rug-pull MCP descriptions with severity-tagged findings and remediation suggestions. Use for…
Agent
Search Apollo for prospects matching an ICP description and return a ranked, enriched lead table. Use when the prospect skill needs to find decision-makers, build a lead list, or any time the user asks to "find leads", "search for prospects", "build a list of CTOs/CEOs/VPs", or describes an ideal customer profile.…
Agent
Find leads matching ICP criteria and bulk-enroll them into an Apollo outreach sequence. Handles prospect search, enrichment, contact creation, deduplication, and enrollment in one isolated flow. Use when the user says "load leads into a sequence", "add contacts to [sequence]", "run sequence-load", or "enroll [N]…
Agent
Fetch structured data from a LinkedIn profile URL, company page, job posting, or person name. Use when any workflow needs LinkedIn data before outreach, enrichment, or research — including when the user says "get their LinkedIn", "look up [name] on LinkedIn", "check [company] on LinkedIn", "scrape this profile", or…
Agent
Read-only Postgres/database analyst. Answers questions by running SELECT-style reads and returning clean summaries — never raw dumps. Writes are hard-blocked by a PreToolUse guard hook. Use proactively whenever a task needs to query data and only needs to READ it. Do NOT use when the task must modify data or run a…