chro-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources such as company-context.md and user-provided JSON configuration files for its analytical scripts. While these are necessary for the skill's function, they represent a potential surface for indirect prompt injection if the ingested files contain adversarial instructions. However, the skill lacks high-privilege capabilities that would allow such an injection to cause significant harm.
- Ingestion points: The agent is instructed to read company-context.md in SKILL.md. The scripts comp_benchmarker.py and hiring_plan_modeler.py ingest user-supplied JSON data via the --config flag.
- Boundary markers: The instructions do not include specific delimiters or warnings to ignore embedded instructions within these files.
- Capability inventory: The skill uses Python scripts to perform calculations and generate reports to standard output. It does not perform sensitive network operations or system-level modifications.
- Sanitization: Input data is parsed through standard JSON and CSV libraries into structured Python dataclasses, providing basic validation but not semantic filtering of instructions.
Audit Metadata