to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions in
SKILL.mdare purely text-based and provide a template for generating project documentation. No executable scripts or binary files are present in the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user conversation data.\n - Ingestion points: conversation context referenced in
SKILL.md.\n - Boundary markers: Absent.\n
- Capability inventory: Repo exploration and issue tracker publishing instructions in
SKILL.md.\n - Sanitization: Absent. The risk of indirect prompt injection is inherent to the skill's primary purpose, and its impact is limited to the content of the generated documentation.\n- [COMMAND_EXECUTION]: Static analysis findings mentioned in
skill-report.json(lines 9 and 19 ofSKILL.md) regarding shell execution are false positives. These lines contain markdown backticks used for inline code styling of a slash command (/setup-matt-pocock-skills) and a triage label (ready-for-agent), not shell command substitution.
Audit Metadata