The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill ingests untrusted user data (resumes and CVs) for analysis. It lacks explicit boundary markers or sanitization to prevent the agent from potentially following instructions embedded within the processed documents. However, the risk is minimized as the skill's capabilities are restricted to text analysis and local reference file reading, and it requires user confirmation before proceeding. Evidence: 1. Ingestion points: User-provided file or pasted text (SKILL.md); 2. Boundary markers: Absent; 3. Capability inventory: Local file reading and text output; 4. Sanitization: Absent.
[Prompt Injection] (SAFE): No instructions were found that attempt to bypass safety filters, extract system prompts, or override agent behavior.
[Data Exposure & Exfiltration] (SAFE): The skill does not contain hardcoded credentials or access sensitive system files. Network operations are absent, and file access is limited to the skill's own reference directory.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download or execute external scripts or packages.
[Obfuscation] (SAFE): No obfuscation techniques, such as Base64 encoding or hidden characters, were detected in any of the skill files.

identify