The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted data from web search results.
Ingestion points: The skill ingests external content via the web_search tool as described in Step 2 of SKILL.md.
Boundary markers: Absent; there are no explicit instructions or delimiters provided to the agent to distinguish between its internal instructions and the potentially malicious content found in search results.
Capability inventory: Low risk; the skill's capabilities are restricted to displaying text and generating links, with no file-system write access, shell execution, or network exfiltration capabilities.
Sanitization: Absent; the skill does not specify any filtering or sanitization of the search results before presenting them to the user.
[SAFE]: The skill uses clear, non-obfuscated language and focuses entirely on its stated purpose of career assistance. It does not attempt to access sensitive system files or environment variables.

job-search