sales-firsto

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses a persistent local file, references/learnings.md, to store and retrieve knowledge gained across different interactions. This creates a surface for indirect prompt injection, where data provided in a past interaction could influence the agent's behavior in future sessions. However, this feature is part of the skill's intended self-improvement functionality and is used in a context that lacks high-risk capabilities (like system shell access), making the risk minimal.- [COMMAND_EXECUTION]: The skill contains markdown documentation providing an npx command line instruction for the user to manually install related functionality. This command targets a package belonging to the same author (sales-skills) as the current skill and is intended for user execution rather than automated execution by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 06:34 PM
Security Audit — agent-trust-hub — sales-firsto