audit
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external URLs and local files without sufficient safeguards.
- Ingestion points: Data enters via the <url|path> argument in SKILL.md which is then processed using WebFetch and Read tools.
- Boundary markers: The skill does not define delimiters or provide explicit instructions to the orchestrator or subagents to treat fetched content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill has access to Bash, Task, and WebFetch tools, which could be abused if malicious instructions in a target website successfully influence the agent's behavior.
- Sanitization: No content filtering, escaping, or validation of the ingested data is described before it is passed to specialist subagents for analysis.
Audit Metadata