earnings-recap
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the
!commandsyntax within SKILL.md to execute a Python one-liner (python3 -c "exec(...)") when the skill is accessed. This code verifies the presence and version of the requiredyfinancelibrary.\n- [COMMAND_EXECUTION]: The skill provides logic to automatically install theyfinancepackage usingpipviasubprocess.check_callif it is missing from the system.\n- [DYNAMIC_EXECUTION]: The environment check implemented in the dynamic context injection block uses the Pythonexec()function to run code from a string literal.\n- [EXTERNAL_DOWNLOADS]: The skill is designed to download theyfinancelibrary from official repositories and fetch stock market data from Yahoo Finance's public services. These downloads are associated with the primary functionality of the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays stock news headlines through theticker.newsattribute. This introduces a surface where an external party could attempt to influence the agent by embedding instructions within news headlines.\n - Ingestion points: The
ticker.newsdata source referenced in SKILL.md (Step 2) and Step 5.\n - Boundary markers: No explicit delimiters or instructions are used to separate the external news content from the agent's core logic.\n
- Capability inventory: The skill allows for the execution of Python scripts and shell commands (via the installation step).\n
- Sanitization: The skill does not perform explicit sanitization or filtering of the news headlines before they are presented to the agent.
Audit Metadata