resume-optimization
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external URLs.
- Ingestion points: The skill uses
WebFetchto retrieve job description content from URLs provided in$ARGUMENTS(SKILL.md). - Boundary markers: The workflow does not define any delimiters or system instructions to ignore embedded commands within the fetched job description.
- Capability inventory: The skill has access to
Read,Write,WebFetch,Glob, andGreptools, allowing it to modify local files based on potentially poisoned external input. - Sanitization: There is no mention of sanitizing or escaping the fetched content before processing.
- EXTERNAL_DOWNLOADS (LOW): The skill utilizes the
WebFetchtool to download data from arbitrary external sources. - Evidence:
SKILL.mdincludesWebFetchin theallowed-toolslist and uses it to fetch job description content if a URL is provided as an argument. - Context: While this is a primary function of the skill, it represents an outbound network request to non-whitelisted domains.
Audit Metadata