lov-bp-deck
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled content from
outline.mdand assets during the rendering workflow. - Ingestion points: Reads
outline.mdand source notes provided by the user in Step 1 and Step 4. - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the user's outline.
- Capability inventory: The skill invokes the
lov-any2decktool, writes files to the local filesystem (deck-manifest.md, PPTX, PDF, images), and performs visual QA. - Sanitization: No explicit sanitization or validation of the outline's content is described before it is passed to the rendering tool.
- [COMMAND_EXECUTION]: The workflow requires the agent to invoke external tools and commands.
- Evidence: Step 4 explicitly instructs the agent to 'Invoke lov-any2deck using the approved outline and chosen style'.
- Evidence: The README.md suggests installation via
npx skills add bp-deck, which involves executing a package runner to add the skill. - [EXTERNAL_DOWNLOADS]: The skill relies on external dependencies and installation processes.
- Evidence: The README.md and SKILL.md identify
lov-any2deckandlov-branding-consistencyas external dependencies required for the skill to function. - Evidence: The workflow assumes these tools are available in the active Agent Skills environment.
Audit Metadata