product-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script,
scripts/okr_cascade_generator.py, to generate OKR cascades. This script uses the standard library to process command-line arguments and does not invoke external processes or perform unsafe shell operations. - [INDIRECT_PROMPT_INJECTION]: The OKR generator script accepts user-provided metrics and interpolates them directly into the output strings. While this script lacks dangerous capabilities, it represents a potential surface where untrusted data could be formatted in a way that influences the agent's context.
- Ingestion points: User input provided via the
--metricsargument inscripts/okr_cascade_generator.pyis used to populate template placeholders. - Boundary markers: The script output lacks explicit delimiters to differentiate between static template text and dynamic user-provided values.
- Capability inventory: All scripts in this skill are restricted to local text processing and do not perform file writes, network operations, or dynamic code execution.
- Sanitization: The
_fill_metricsfunction in the generator script performs direct string replacement without validation or escaping of the input values.
Audit Metadata