pptx-presentation-builder
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-controlled data via the deck_brief input, creating a surface for indirect prompt injection. \n
- Ingestion points: The deck_brief YAML structure in SKILL.md. \n
- Boundary markers: Present; the skill employs Markdown headers and YAML delimiters to separate user data from instructions. \n
- Capability inventory: Access to Bash and Write tools allows the agent to create files and execute local commands. \n
- Sanitization: Absent; the instructions do not specify explicit sanitization or validation of the brief content.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform file operations and handle export tasks like creating the assets.zip package. This behavior is restricted to the local environment and aligns with the tool's intended purpose.
- [SAFE]: No malicious patterns, obfuscation, or high-risk command execution were detected during the analysis.
Audit Metadata