modspec-implement
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted data from external specification and feature files.
- Ingestion points: The skill explicitly instructs the agent to read files from the
spec/andfeatures/directories (SKILL.md). - Boundary markers: There are no instructions to use delimiters or ignore embedded instructions when reading these external files.
- Capability inventory: The skill requires the agent to write implementation code to the local filesystem and execute test runners/feature suites (SKILL.md, Steps 4 and 6).
- Sanitization: There is no mention of sanitizing, validating, or escaping the content of the
.mdor.featurefiles before the agent acts upon their instructions.
Audit Metadata