report
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from the
input/directory to generate reports, creating an indirect prompt injection surface. - Ingestion points: Untrusted data is read from files in
input/<dataset>/using theReadandGlobtools as specified in the instructions. - Boundary markers: The report assembly instructions (Step 4) do not define delimiters or instructions for the agent to ignore embedded commands within the processed data.
- Capability inventory: The skill has access to
Bash,Write, andEdittools, which provide a high-impact capability set if the agent inadvertently follows instructions found within data files. - Sanitization: There is no evidence of data validation, escaping, or filtering before interpolation into the Markdown report templates.
Audit Metadata