modernpython
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read and analyze Python source code provided via file paths in the arguments, which introduces a risk of processing malicious instructions embedded in the data.
- Ingestion points: In
SKILL.md, the instructions explicitly state to 'Read each file' based on paths provided in the$ARGUMENTSvariable. - Boundary markers: The skill uses
<modernization_targets>tags to wrap the input arguments, but it lacks explicit instructions telling the agent to treat the content of the files strictly as data or to ignore any natural language instructions that might be hidden in comments or strings within the code. - Capability inventory: The skill is intended to identify legacy patterns and report recommended changes. While it does not include dangerous tools in its frontmatter, the output of the analysis could be used to influence subsequent agent actions.
- Sanitization: No sanitization, escaping, or filtering of the external file content is performed before it is presented to the language model for review.
Audit Metadata