recruitment-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing external data such as resumes, candidate profiles, and platform-specific communications. This creates an inherent surface where malicious instructions embedded in these external documents could potentially influence the agent's behavior.
- Ingestion points: Resume screening workflows and the recruitment data analysis class (
RecruitmentFunnelAnalyzer) defined inSKILL.md. - Boundary markers: The skill does not provide delimiters or instructions to ignore embedded commands in candidate data.
- Capability inventory: The skill currently specifies no tool usage, network operations, or sensitive file access.
- Sanitization: There are no provisions for sanitizing or filtering input from processed resumes or candidate profiles.
- [METADATA_POISONING]: There is an inconsistency between the platform-provided author identity ('itzfaisal') and the author specified in the skill's YAML frontmatter ('agency-agents'). While likely a template artifact, it represents a minor metadata discrepancy.
Audit Metadata