paper-comic

Warn

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's workflow relies on executing a script from an external skill directory using npx -y bun "$SKILL_DIR/scripts/main.ts". This involves running code from a dynamically determined path on the local filesystem.
  • [EXTERNAL_DOWNLOADS]: The use of npx -y can trigger the automatic download of the bun runtime or other Node.js packages from the npm registry if they are not present on the host system.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from academic papers to drive the creative generation process.
  • Ingestion points: The skill reads paper content from PDF or Markdown files provided by the user in Step 1 of the workflow.
  • Boundary markers: There are no explicit delimiters or instructions provided to the LLM to ignore potentially malicious instructions embedded within the paper text during the storyboard and character design phases.
  • Capability inventory: The skill has the capability to execute shell commands (via npx) and generate files in the local filesystem.
  • Sanitization: No sanitization or filtering of the input paper content is mentioned before it is interpolated into prompts for generating outlines, characters, and image descriptions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 07:16 AM