workflow-automation-roi-estimator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external JSON or CSV data which represents a surface for indirect prompt injection. If an attacker embeds instructions within the data files, the agent might inadvertently follow them when processing the skill's output.
- Ingestion points: The
run.pyscript reads file content from a user-specified path usinginput_path.read_text(). - Boundary markers: The skill does not employ specific delimiters or warnings to ignore instructions embedded in the data.
- Capability inventory: The skill has file system capabilities including reading files (
read_text), creating directories (mkdir), and writing files (write_text) withinrun.py. - Sanitization: No content validation or sanitization is performed on the ingested data before processing.
Audit Metadata