tsg-flow-frontend-techspec-creator
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data from Product Requirement Documents (PRD) and API contracts to generate technical documentation.
- Ingestion points: Reads from
tasks/prd-[slug]/prd.mdandapi-contract.yaml. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore malicious instructions embedded within the source documents.
- Capability inventory: The agent has file writing capabilities to produce
frontend-techspec.mdanddocs/adr/adr-NNN.md. - Sanitization: The instructions do not mention any validation or filtering of the content extracted from the input files.
- [COMMAND_EXECUTION]: The templates provided by the skill suggest the use of external CLI tools via
npxfor common developer tasks. - Evidence: Templates include commands for
npx openapi-typescriptfor type generation andnpx @stoplight/prism-clifor API mocking. These are well-known developer tools and their use is documented neutrally as part of the intended frontend development workflow.
Audit Metadata