takt-task-builder
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to fetch content from GitHub Issues (Step 1 and Step 4 in
SKILL.md) and use it to generate task files. Maliciously crafted issue content could potentially influence the agent's behavior during this process. - Ingestion points:
SKILL.mdinstructions and documentation refer to fetching title, body, and comments from GitHub Issues via theghCLI. - Boundary markers: The skill uses markdown templates but lacks explicit boundary markers or instructions telling the agent to ignore embedded commands within the fetched content.
- Capability inventory: The agent has the capability to write files to the local filesystem and execute a local bash script for validation.
- Sanitization: No explicit sanitization or filtering of fetched issue data is performed before interpolation into prompts.
- [COMMAND_EXECUTION]: The skill provides a shell script (
scripts/validate-order-md.sh) and directs the agent to execute it to verify the structure and formatting of the generated task specifications. The script performs local file reading and pattern matching using standard system utilities.
Audit Metadata