extract-webpage-data
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [DATA_EXPOSURE]: The skill reads API credentials from
~/.gooseworks/credentials.json. This is the standard mechanism for the skill to authenticate with its own backend services provided by the vendor. - [COMMAND_EXECUTION]: The skill uses
python3 -ccommands to parse the local JSON credential file and set environment variables. This is a common pattern for configuration management in shell environments. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web pages that are not under the user's control.
- Ingestion points: Content retrieved from external URLs via Scrapegraph, Olostep, or Riveter APIs (SKILL.md).
- Boundary markers: None identified. The instructions do not define delimiters or warnings for the agent to ignore instructions embedded within the scraped content.
- Capability inventory: The skill uses
curlfor network operations to communicate with the extraction APIs (SKILL.md). - Sanitization: There is no evidence of sanitization or filtering of the extracted web content before it is processed by the agent.
Audit Metadata