sales-ccaas-selection

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill features an automated learning mechanism that is susceptible to indirect prompt injection.\n
  • Ingestion points: User requirements and interaction feedback (Step 1 and Step 4).\n
  • Boundary markers: Absent; user-provided feedback is appended directly to references/learnings.md and read back without delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: Reading and writing to local files and routing to other platform-specific skills.\n
  • Sanitization: Absent; the skill does not implement validation or filtering for the content persisted to the learning reference file.\n- [COMMAND_EXECUTION]: The documentation provides a command for users to install related skills from the author's own infrastructure.\n
  • Evidence: npx skills add sales-skills/sales --skill sales-do -a claude-code -y in SKILL.md.\n- [EXTERNAL_DOWNLOADS]: The skill references the download and installation of additional tools from the author's repository.\n
  • Evidence: sales-skills/sales repository reference for the sales-do skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 07:04 PM