execute
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands using the 'doctrine' CLI tool for managing slice status, worktree forks, and merging ('landing') branches. It also uses 'cargo clippy' for code linting.
- [PROMPT_INJECTION]: The skill processes untrusted external data from files such as 'design.md', 'plan.toml', and phase-specific markdown sheets to guide its execution steps. This creates an indirect prompt injection surface where malicious instructions within those files could influence agent behavior.
- Ingestion points: Reads content from 'state/.../phases/phase-NN.md', 'plan.toml', 'plan.md', 'design.md', and 'slice-nnn.md' to determine entrance criteria and implementation details.
- Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore potentially malicious embedded content within the ingested files.
- Capability inventory: The skill has access to the 'doctrine' CLI for repository and worktree management, git for commits and merges, and 'cargo' for linting and building.
- Sanitization: Absent. There is no evidence of filtering or validation of the content read from the external project files before it is used to guide the implementation phase.
Audit Metadata