project-specification
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to bypass user confirmation during automated workflow transitions ("Do NOT prompt the user for confirmation"), which reduces human oversight and could allow for unintended execution of subsequent phases.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project briefs from external sources which may contain embedded instructions designed to influence the specification output or the behavior of downstream skills.
- Ingestion points: Untrusted project briefs processed in SKILL.md.
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded content within the brief.
- Capability inventory: File system writes to
docs/specification.mdanddocs/tradeoffs.md, and invocation of other skills (e.g.,Skill(attune:project-planning)). - Sanitization: Absent; the skill does not specify validation or escaping for the ingested content.
Audit Metadata