product-manager-toolkit
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Python scripts (
rice_prioritizer.pyandcustomer_interview_analyzer.py) to perform its primary functions. These scripts are executed locally with user-provided data files. - [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection by processing untrusted external data.
- Ingestion points: Data enters the context via
features.csv,interview_transcript.txt, and other user-supplied files mentioned inSKILL.md. - Boundary markers: The documentation does not specify the use of delimiters or specific warnings to ignore instructions embedded within the processed transcripts or feature lists.
- Capability inventory: The skill possesses the capability to execute commands via Python scripts to process the ingested data.
- Sanitization: There is no evidence in the skill's instructions regarding the sanitization or validation of the text content within the input files.
Audit Metadata