saas-metrics
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains an instruction for the agent to automatically inspect the user's local environment upon activation. It runs a directory listing (ls) on several common skill installation paths (e.g., ~/.claude/skills/, ~/.agent/skills/) to identify if recommended companion skills are already installed. This check is used to suggest relevant additional tools from the AbsolutelySkilled vendor collection.
- [PROMPT_INJECTION]: The skill is designed to process untrusted external data such as raw subscription logs and financial spreadsheets, which represents a surface for indirect prompt injection.
- Ingestion points: Subscription data and spreadsheet files provided by the user for analysis (referenced in SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within user-provided data.
- Capability inventory: The skill's primary functions are text generation and metrics calculation; its only shell interaction is the automated discovery of other skills via the ls command.
- Sanitization: There are no instructions for sanitizing, validating, or escaping content found within processed data files.
Audit Metadata