Skills
skills/oschina/gitee-agent-skills/quick-fix-suggestion/Gen Agent Trust Hub

quick-fix-suggestion

Fail

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill documentation explicitly provides patterns to locate sensitive files containing credentials or secrets.
  • Evidence: The file references/TOOL_REFERENCE.md includes the pattern glob('**/.env*', { cwd: repoPath }) under the 'Find Configuration Files' section.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion of untrusted data from Gitee issues and comments.
  • Ingestion points: Untrusted data enters the agent context via get_repo_issue_detail and list_issue_comments tools as described in SKILL.md.
  • Boundary markers: There are no delimiters or instructions to ignore embedded commands within the ingested issue data.
  • Capability inventory: The agent has access to bash, read, grep, and ast_grep_search tools (detailed in SKILL.md and references/TOOL_REFERENCE.md).
  • Sanitization: No evidence of sanitization, escaping, or validation of the external content is provided.
  • [COMMAND_EXECUTION]: The skill uses the bash tool to execute shell commands for repository history analysis.
  • Evidence: references/TOOL_REFERENCE.md includes a code snippet for executing git log via the bash tool.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 19, 2026, 02:28 AM