client-packet-engine
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests large amounts of untrusted data from external sources, creating an attack surface where malicious instructions hidden in scraped content could influence agent behavior.
- Ingestion points: Untrusted data enters the agent context via
review-scraper,linkedin-post-research,web-archive-scraper,conference-speaker-scraper, and general web fetching for company validation (SKILL.md). - Boundary markers: The instructions lack explicit delimiters or specific warnings for the agent to ignore instructions potentially embedded within the scraped content.
- Capability inventory: The skill has permissions to write to the local file system (
clients/directory), perform further network operations for research, and generate outreach content such as email drafts (SKILL.md). - Sanitization: No evidence of sanitization, escaping, or filtering of external content is present in the pipeline before the data is interpolated into strategy generation prompts.
Audit Metadata