devops-deploy-v2

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches dependencies using pip install and incorporates official GitHub Actions for environment setup and code coverage analysis.
  • [COMMAND_EXECUTION]: Runs deployment and build commands through the AWS SAM CLI, including sam build and sam deploy.
  • [DATA_EXFILTRATION]: Sends deployment status updates to the Telegram API using curl. This operation utilizes environment secrets for authentication.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through the processing of local project files like requirements.txt and the src/ directory (SKILL.md).
  • Boundary markers: No delimiters or warnings are present to prevent the agent from following instructions that might be embedded in these files.
  • Capability inventory: The skill allows the agent to execute shell commands, perform network operations via curl, and write files (SKILL.md).
  • Sanitization: No input validation or escaping is applied to the content retrieved from processed files before it is used in command execution or prompt interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 11:33 AM
Security Audit — agent-trust-hub — devops-deploy-v2