improve-content
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of fetching and analyzing third-party web content.
- Ingestion points: In
SKILL.md, Step 1 instructions direct the agent to fetch a user-provided URL and read the full rendered page content into its context. - Boundary markers: Absent. There are no delimiters or explicit system instructions to treat the fetched content purely as data or to ignore any instructions embedded within it.
- Capability inventory: The skill utilizes tool-based web fetching and search engine research (SERP). It does not have access to sensitive local files, shell command execution, or the ability to write to the local file system.
- Sanitization: Absent. The skill does not perform any pre-processing or filtering on the content retrieved from the URL before it is used to generate the rewritten article.
Audit Metadata