skills/jdrhyne/agent-skills/gsc/Gen Agent Trust Hub

gsc

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The script scripts/gsc_auth.py is designed to print sensitive OAuth credentials—specifically the GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, and GOOGLE_REFRESH_TOKEN—directly to the standard output. While intended for initial configuration, an agent executing this script would cause these secrets to be recorded in the interaction history or logs, leading to potential exposure.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the data it retrieves from external sources.\n
  • Ingestion points: The scripts/gsc_query.py script fetches data such as search queries and page URLs from the Google Search Console API.\n
  • Boundary markers: The skill lacks any boundary markers or instructional delimiters to separate retrieved search data from the agent's instructions.\n
  • Capability inventory: The skill facilitates the execution of Python scripts and shell commands via the definitions in SKILL.md.\n
  • Sanitization: There is no evidence of sanitization, filtering, or escaping applied to the search queries or other metadata retrieved from the GSC API before they are printed or processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:27 AM