apify-fix-git-connection

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes actor build logs (retrieved via apify api GET '/v2/actor-builds/<buildId>/log') which are external, untrusted sources that could technically contain malicious instructions.\n
  • Ingestion points: Build logs retrieved from the Apify API.\n
  • Boundary markers: The skill defines high-level rules such as 'Ask before a deploy' and 'Tokens stay with the user', which act as procedural guardrails, though it lacks technical delimiters for the log content.\n
  • Capability inventory: The skill can trigger builds, update version metadata, and perform Git pushes.\n
  • Sanitization: No explicit sanitization or filtering is applied to the retrieved log data before processing.\n- [COMMAND_EXECUTION]: The skill utilizes the Apify CLI, GitHub CLI, and Git for diagnostic and repair tasks. These are appropriate for the skill's purpose, and the instructions explicitly emphasize user review and manual handling of secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 09:10 AM