gjalla-spec-review
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions designed to guide an AI agent through a specification review process. It does not contain any executable scripts, binaries, or configuration files that could perform unauthorized operations.
- [INDIRECT_PROMPT_INJECTION]: As the skill is designed to ingest and analyze external documentation (software plans and specifications), it possesses an inherent surface for indirect prompt injection. A malicious specification could theoretically contain instructions to bias the review process. However, the skill lacks any active capabilities or tool access that would allow such an injection to result in technical harm.
- Ingestion points: External software specifications, technical plans, and design documents provided by the user for review in
SKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used to isolate the untrusted input from the skill's instructions.
- Capability inventory: The skill is restricted to generating textual analysis and reports. It has no capability to write files, execute shell commands, or perform network operations.
- Sanitization: No input validation or sanitization is performed on the ingested content.
Audit Metadata