templ
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review
.templsource files, creating an attack surface where instructions embedded within the code could influence agent behavior. - Ingestion points: The agent is triggered whenever a
.templfile is edited or reviewed, as described inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters provided to isolate code content from agent instructions.
- Capability inventory: The skill assumes the agent can execute commands like
templ generateandtempl fmt, and perform file system operations. - Sanitization: No sanitization logic for ingested code is specified in the prompt instructions.
- [EXTERNAL_DOWNLOADS]: The
.dev/reference-inventory.jsonfile contains a list of URLs pointing to documentation in the a-h/templ repository on GitHub. These references are used for documentation purposes and do not represent executable code downloads.
Audit Metadata