The Agent Skills Directory

[SAFE]: The skill's instructions strictly focus on the stated purpose of job searching, providing clear logic for input parsing, search keyword generation, and data filtering.
[EXTERNAL_DOWNLOADS]: The skill references a comprehensive list of external URLs in references/platforms.md. All identified domains (e.g., job.mohrss.gov.cn, sasac.gov.cn, iguopin.com, zhipin.com) are legitimate Chinese government or recruitment services. These references are documented neutrally as they align with the skill's primary function.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by fetching content from external websites to verify job details.
Ingestion points: Step 4 in SKILL.md uses web_fetch to retrieve external job announcement text.
Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions within the fetched data.
Capability inventory: The skill uses the web_fetch tool. It does not possess high-risk capabilities such as file system writes, shell execution, or access to sensitive local environment data.
Sanitization: None specified; however, the agent is instructed to extract specific structured fields (salary, requirements, contact info), which limits the impact of potential injection content.

taxue-job-search