prowler-compliance

Warn

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The script assets/sync_framework.py uses importlib.import_module to load parser modules based on strings retrieved from the framework configuration YAML (parser.module). This implementation allows for dynamic loading of code from computed paths within the local package structure.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process compliance catalogs from external sources (such as FINOS CCC). Processing this untrusted data creates a potential surface for indirect prompt injection.
  • Ingestion points: Data is ingested via sync_framework.py from external YAML files stored in a temporary directory.
  • Boundary markers: There are no explicit instructions or delimiters used to separate requirement text from agent instructions.
  • Capability inventory: The skill is authorized to use Bash, Edit, Write, and WebFetch tools.
  • Sanitization: The skill uses yaml.safe_load for parsing but does not sanitize the semantic content of the compliance requirements.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 2, 2026, 04:40 PM