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.pyusesimportlib.import_moduleto 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.pyfrom 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, andWebFetchtools. - Sanitization: The skill uses
yaml.safe_loadfor parsing but does not sanitize the semantic content of the compliance requirements.
Audit Metadata