systematic-debugging— agent skill

systematic-debugging — independently scanned and version-tracked by SaferSkills.

by GanyuanRan·Agent Skill·github.com/GanyuanRan/Aegis

Is systematic-debugging safe to install?

SaferSkills independently audited systematic-debugging (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 2 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
45/100
●●●●●○○○○○
↑ +0 since first scan (45 → 45)Re-scan~30s
Latest scan
ScannedJun 27, 2026 · 26d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings3 warnings · 2 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
14
4.9 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 5 flagged

Securityscore 14 · 5 findings
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · README.en.md
HIGHonce decoded by the agent, an encoded payload has the same impact class as plain-text injection.
Why it matters

A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.

The exact value spotted
excerptREADME.en.md· markdown
2<a href="https://linux.do/t/topic/2108966/20" alt="LINUX DO">
3<img
4src="https://img.shields.io/badge/LINUX-DO-FFB003.svg?logo=data:image/svg%2bxml;base64,DQo8c
… (96 chars elided on L4)
5<a href="https://dev.to/_879c5a0279451d52e43c3/aegis-a-method-pack-for-more-reliable-ai-codi
… (29 chars elided on L5)
6<img src="https://img.shields.io/badge/DEV.to-Article-0A0A0A?logo=devdotto&logoColor=white"
… (6 chars elided on L6)
Occurrences
1 occurrence · at L4
How to fix
Remove the encoded blob, or decode it and review what it actually contains.
  1. Decode the base64 string and confirm it is not an instruction directed at the agent.
  2. Move any legitimate binary or signature data into a dedicated file (*.sig, SIGNATURES) outside the documentation.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-B64-PAYLOAD-01sha25631792e4fb4063c27rubric 365aacaView on GitHub
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · README.md
HIGHonce decoded by the agent, an encoded payload has the same impact class as plain-text injection.
Why it matters

A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.

The exact value spotted
excerptREADME.md· markdown
2<a href="https://linux.do/t/topic/2108966/20" alt="LINUX DO">
3<img
4src="https://img.shields.io/badge/LINUX-DO-FFB003.svg?logo=data:image/svg%2bxml;base64,DQo8c
… (96 chars elided on L4)
5<a href="https://dev.to/_879c5a0279451d52e43c3/aegis-a-method-pack-for-more-reliable-ai-codi
… (29 chars elided on L5)
6<img src="https://img.shields.io/badge/DEV.to-Article-0A0A0A?logo=devdotto&logoColor=white"
… (6 chars elided on L6)
Occurrences
1 occurrence · at L4
How to fix
Remove the encoded blob, or decode it and review what it actually contains.
  1. Decode the base64 string and confirm it is not an instruction directed at the agent.
  2. Move any legitimate binary or signature data into a dedicated file (*.sig, SIGNATURES) outside the documentation.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-B64-PAYLOAD-01sha25631792e4fb4063c27rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/systematic-debugging/test-pressure-1.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptskills/systematic-debugging/test-pressure-1.md· markdown
1# Pressure Test 1: Emergency Production Fix
2 
3**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questi
… (33 chars elided on L3)
4 
5You have access to: skills/debugging/systematic-debugging
Occurrences
1 occurrence · at L3
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25615dae9807bd892c6rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/systematic-debugging/test-pressure-2.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptskills/systematic-debugging/test-pressure-2.md· markdown
1# Pressure Test 2: Sunk Cost + Exhaustion
2 
3**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questi
… (33 chars elided on L3)
4 
5You have access to: skills/debugging/systematic-debugging
Occurrences
1 occurrence · at L3
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25615dae9807bd892c6rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/systematic-debugging/test-pressure-3.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptskills/systematic-debugging/test-pressure-3.md· markdown
1# Pressure Test 3: Authority + Social Pressure
2 
3**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questi
… (33 chars elided on L3)
4 
5You have access to: skills/debugging/systematic-debugging
Occurrences
1 occurrence · at L3
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25615dae9807bd892c6rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.