browse-x
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from public X (Twitter) posts, threads, and profiles. This external, untrusted content is passed into the agent's context, which could potentially contain adversarial instructions meant to influence the agent's behavior.
- Ingestion points: The
scripts/browse-x.shscript fetches content from the external API atx.pcstyle.dev. - Boundary markers: The script does not implement explicit delimiters or boundary markers to separate the untrusted external content from the agent's primary instructions.
- Capability inventory: The skill utilizes network access via
curland shell execution viaBash. - Sanitization: No sanitization or filtering of the retrieved content is performed before it is output to the agent.
- [COMMAND_EXECUTION]: The skill uses a bash script (
scripts/browse-x.sh) to construct and executecurlcommands. The script includes logic to safely encode parameters using--data-urlencode, which is a good security practice for preventing command injection via user-supplied arguments.
Audit Metadata