The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (job descriptions and resume inputs), which allows for potential indirect prompt injection attacks. \n- Ingestion points: Job descriptions and user-supplied resume text mentioned in SKILL.md. \n- Boundary markers: No delimiters or instructions are used to isolate user data. \n- Capability inventory: No tools or command execution capabilities are defined within the skill. \n- Sanitization: No validation or sanitization of input data is defined. \n- [METADATA_POISONING]: The author field is defined as Claude Code, while the skill is attributed to inbharatai in the collection link, which is misleading metadata.

resume-builder