add-webcodecs-bug
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external, user-provided bug tracker URLs (e.g., Chromium, WebKit, or Firefox issue pages) and incorporates that data into local documentation.
- Ingestion points: Data enters the agent's context through the
browser:control-in-app-browsertool when visiting external issue URLs as described inSKILL.md. - Boundary markers: There are no explicit instructions to ignore or delimit embedded instructions that might be present in the external issue descriptions or comments.
- Capability inventory: The skill has the capability to write to the local file system at the path
packages/docs/docs/mediabunny/webcodecs-bugs.mdx. - Sanitization: No specific sanitization or validation logic is provided to filter out potentially malicious instructions from the external bug report content before writing it to the markdown file.
Audit Metadata