observability-instrument-with-otel

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes Python scripts (add_tracing.py, analyze_traces.py, validate_instrumentation.py) designed to be executed via the Bash tool to modify or analyze local source code. This is the primary function of the skill and no suspicious commands were found.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection because its code modification scripts process local source code.
  • Ingestion points: The add_tracing.py script reads and parses local Python source files provided as command-line arguments.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are used during file processing.
  • Capability inventory: The script uses the ast module to parse and transform code and the open() function to write modified content back to the filesystem.
  • Sanitization: Function and method names are extracted and used to construct log message strings; while these are stored as string constants in the resulting AST, they are not sanitized against potentially malicious method names in the source files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:24 PM