skills/pc-style/x-md/browse-x/Gen Agent Trust Hub

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.sh script fetches content from the external API at x.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 curl and shell execution via Bash.
  • 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 execute curl commands. 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
Risk Level
SAFE
Analyzed
Sep 7, 2026, 05:19 PM
Security Audit — agent-trust-hub — browse-x