scan-and-profile
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions describe processing untrusted external data which can serve as an injection vector if the data contains malicious instructions targeting the agent or the user.
- Ingestion points: External data enters the agent context through the
dataparameter in thepb.DataScan,pb.preview,pb.missing_vals_tbl, andpb.schema_from_tblfunctions mentioned in SKILL.md and the reference files. - Boundary markers: No explicit instructions or delimiters are provided to the agent to ignore or neutralize instructions that may be embedded within the processed datasets.
- Capability inventory: The skill includes the ability to write files to the local file system using
save_to_jsonas described in SKILL.md and datascan-reference.md. - Sanitization: There is no evidence of input sanitization or schema validation performed on the ingested data before profiling occurs.
- [NO_CODE]: The skill consists entirely of Markdown documentation and reference files. No executable scripts, binaries, or configuration files that trigger code execution are included in the skill package.
Audit Metadata