mission-specify
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation, which can be a vector for indirect prompt injection if the source file contains malicious instructions.
- Ingestion points: The skill reads content from 'brief.md' to generate 'spec.md'.
- Boundary markers: No explicit delimiters or boundary markers are used to encapsulate the data from 'brief.md'.
- Capability inventory: The skill uses 'adlc-cli' for workflow state management and execution, writes to 'spec.md', and references local execution scripts like 'run-branch.sh'.
- Sanitization: There is no evidence of sanitization or validation of the content ingested from 'brief.md'.
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute shell commands using 'adlc-cli' for workflow orchestration and state management. These commands are vendor-specific to 'tikalk' and align with the skill's intended functionality.
Audit Metadata