package-upgrade
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection as it ingests untrusted data from external sources and local files. \n
- Ingestion points: Local
package.jsonfiles and external content retrieved viaWebSearchandWebFetch(e.g., from npmjs.com and github.com). \n - Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore instructions within the ingested content. \n
- Capability inventory: The agent has access to
Bash,Write,Edit,WebFetch, andTasktools. \n - Sanitization: Absent. The skill lacks sanitization or validation of the data retrieved before processing it into reports.
Audit Metadata