canvas-capture-extension

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script rebuild-extension.sh executes bun run make within the directory specified by the --repo argument or an auto-detected path. This allows for arbitrary code execution if the agent is directed to process a malicious repository.
  • [DATA_EXFILTRATION]: Both SKILL.md and scripts/rebuild-extension.sh contain hardcoded absolute paths pointing to a specific user's home directory (/Users/jonathanburger/...). This exposes local environment details and user identity information within the skill instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon external repository paths provided by the agent or user, which are then used to trigger command execution.
  • Ingestion points: The --repo, --install-dir, and --browser-executable arguments in rebuild-extension.sh (referenced in SKILL.md).
  • Boundary markers: Absent. There are no instructions to verify the source of the repository before building.
  • Capability inventory: The skill performs file system modifications (mkdir -p, cp -R) and invokes a build tool (bun run).
  • Sanitization: The script performs basic existence checks for package.json but does not validate the content or safety of the build instructions within that package.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 01:45 AM
Security Audit — agent-trust-hub — canvas-capture-extension