craig-lead-research-pl
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and summarize information from external, third-party sources such as LinkedIn, job boards (justjoin.it, nofluffjobs.com, pracuj.pl), and business registries (KRS, Rejestr.io). This creates a surface where malicious instructions hidden in those external sites could influence agent behavior.
- Ingestion points: Web content from various job boards, social media, and business registries as specified in the research guidelines in
SKILL.md. - Boundary markers: Absent; the skill does not suggest using delimiters to separate external data from the prompt context.
- Capability inventory: The skill itself contains no scripts or tools, but guides the use of the agent's native browsing and research capabilities.
- Sanitization: No filtering or validation logic is proposed for the data retrieved from external sources.
Audit Metadata