sales-reclaim

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses a persistent file references/learnings.md to store and retrieve 'accumulated platform knowledge', which creates an indirect prompt injection surface (Category 8).
  • Ingestion points: The agent is instructed to read references/learnings.md at the start of every interaction to gather context.
  • Boundary markers: None are present; the content is integrated directly into the agent's operational context without delimiters.
  • Capability inventory: The skill has the capability to append new discoveries, workarounds, or 'gotchas' to the learnings file at the end of an interaction.
  • Sanitization: There is no evidence of validation or sanitization for the content before it is written to or read from the persistent file.
  • [COMMAND_EXECUTION]: The 'Related skills' section in SKILL.md recommends the command npx skills add sales-skills/sales --skill sales-do. While this involves remote package execution, the target package belongs to the skill's author, sales-skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 04:16 PM
Security Audit — agent-trust-hub — sales-reclaim