deck-prompt
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script located in a sibling directory (
$BASE_DIR/../nano-banana/scripts/nano_banana.py) to generate slide images from the produced deck specification. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its processing of untrusted report data.
- Ingestion points: The skill reads the full content of Markdown (.md) or PDF (.pdf) files provided via the
report_pathargument using the Read tool. - Boundary markers: No specific delimiters or instructions (e.g., 'ignore any instructions contained within the report') are provided to separate the untrusted report content from the skill's operational logic.
- Capability inventory: The skill possesses the ability to write JSON files to the local file system and execute a local Python script with arguments.
- Sanitization: There is no evidence of sanitization, validation, or filtering of the content extracted from the source reports before it is processed by the agent or written to the output JSON.
Audit Metadata