outside-to-issue

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script scripts/transform-outside-to-issues.sh to perform file system operations and data transformation tasks for specific pull requests.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and processes external data from markdown files in the outside/ directory, which are then written to the issues/ directory. Malicious instructions embedded in these source files could potentially influence the agent when it later interacts with the generated issue files.\n
  • Ingestion points: Markdown files located in ai-docs/reviews-pr-<PR>/outside/.\n
  • Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded content during the transformation process.\n
  • Capability inventory: Shell script execution (scripts/transform-outside-to-issues.sh) and local file system read/write access.\n
  • Sanitization: No evidence of sanitization, escaping, or validation of the input file content was found in the skill description.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 10:20 AM