tam-sam-som-calculator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, including website copy, marketing emails, and product descriptions, to extract market context for analysis. This creates a surface for indirect prompt injection if the ingested text contains malicious instructions.
- Ingestion points: Untrusted data enters the agent context in 'Step 0: Gather Context' within
SKILL.mdwhere the user is prompted to paste marketing and product materials. - Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings when processing this external content.
- Capability inventory: The agent has the capability to execute a local Python script (
scripts/market-sizing.py) and perform text analysis/generation based on the input. - Sanitization: There is no evidence of input validation, filtering, or escaping of the external content before it is interpolated into the agent's context.
- [COMMAND_EXECUTION]: The skill documentation in
SKILL.mdprovides explicit instructions for the agent or user to execute a local Python script (scripts/market-sizing.py) via the shell for deterministic calculations. The script itself is restricted to standard libraries and basic arithmetic, but it constitutes an intended use of command execution capabilities.
Audit Metadata