The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by interpolating untrusted data into its synthesis process.
Ingestion points: The agent is instructed to read exploration/captures/DISCOVERY_REPORT.md and user Q&A transcripts as the primary source for generating specifications.
Boundary markers: The instructions lack specific delimiters or instructions to treat the contents of the discovery report as untrusted data, which could allow embedded malicious instructions to influence the agent's behavior during the synthesis phase.
Capability inventory: The skill has access to Bash, Read, and Write tools, enabling it to execute shell commands and modify the file system.
Sanitization: There is no evidence of input validation, escaping, or sanitization of the content read from the discovery reports before it is processed or written to the /specs directory.

vibe-togaf-architect