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 annpxcommand 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