unslop
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from potentially untrusted third-party repositories and uses this data to drive agent actions and shell execution.
- Ingestion points: The agent is instructed to read source code, package manifests, CI commands, and documentation to establish a baseline and map project structure (SKILL.md Step 1 and 2).
- Boundary markers: The instructions do not define specific delimiters or instructions to treat the repository content as untrusted data during analysis, potentially allowing malicious code comments to influence the agent.
- Capability inventory: The skill allows the agent to modify source files, remove dependencies, and execute shell-based test runners and build scripts (SKILL.md Step 4).
- Sanitization: There is no process defined for sanitizing repository content before it is processed by the agent or passed to execution tools.
- [COMMAND_EXECUTION]: The skill executes arbitrary commands provided by the project's local environment or build configuration.
- Evidence: Instructions in SKILL.md require the agent to "Run the test suite, build, and the app's critical flows" to establish a behavior baseline and verify batches.
Audit Metadata